From bbc547ad8de76398d625253a3b25d097b88fff48 Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Fri, 26 Apr 2024 15:39:00 +0200 Subject: [PATCH 01/22] 2nd round of benchmark modifications (tiny adjustements to avoid overloading the host). (#1816) # What does this PR do? Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. --- load_tests/common.js | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/load_tests/common.js b/load_tests/common.js index 80728214..e0a10595 100644 --- a/load_tests/common.js +++ b/load_tests/common.js @@ -26,23 +26,23 @@ export function get_options() { // }], }, scenarios: { - single_user: { + // single_user: { + // executor: 'constant-arrival-rate', + // duration: '60s', + // preAllocatedVUs: 1, + // rate: 20, + // timeUnit: '1s', + // }, + load_test: { executor: 'constant-arrival-rate', duration: '60s', - preAllocatedVUs: 1, + preAllocatedVUs: 100, rate: 1, timeUnit: '1s', }, - // load_test: { - // executor: 'constant-arrival-rate', - // duration: '60s', - // preAllocatedVUs: 100, - // rate: 1, - // timeUnit: '1s', - // }, // breakpoint: { // executor: 'ramping-arrival-rate', //Assure load increase if the system slows - // preAllocatedVUs: 1000, + // preAllocatedVUs: 300, // stages: [ // { duration: '60s', target: 100 }, // just slowly ramp-up to a HUGE load // ], From f9cf3456250e420af65e1d813ccee6af749658ad Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Fri, 26 Apr 2024 15:44:44 +0200 Subject: [PATCH 02/22] Adding new env variables for TPU backends. (#1755) # What does this PR do? On TPU (and probably inferentia). The model needs to know right off the bat about BATCH_SIZE and MAX_TOTAL_TOKENS (since the entire cache will be determined by both). This PR sends that information to the shards to they can allocate accordingly. Should be no-op for other backends. Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. --- launcher/src/main.rs | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/launcher/src/main.rs b/launcher/src/main.rs index 40e7364f..f264e000 100644 --- a/launcher/src/main.rs +++ b/launcher/src/main.rs @@ -448,6 +448,8 @@ fn shard_manager( cuda_memory_fraction: f32, rope_scaling: Option, rope_factor: Option, + max_total_tokens: usize, + max_batch_size: Option, otlp_endpoint: Option, status_sender: mpsc::Sender, shutdown: Arc, @@ -512,6 +514,7 @@ fn shard_manager( (Some(scaling), Some(factor)) => Some((scaling, factor)), (None, Some(factor)) => Some((RopeScaling::Linear, factor)), }; + // OpenTelemetry if let Some(otlp_endpoint) = otlp_endpoint { shard_args.push("--otlp-endpoint".to_string()); @@ -564,6 +567,14 @@ fn shard_manager( envs.push(("ROPE_FACTOR".into(), factor.to_string().into())); } + envs.push(( + "MAX_TOTAL_TOKENS".into(), + max_total_tokens.to_string().into(), + )); + if let Some(max_batch_size) = max_batch_size { + envs.push(("MAX_BATCH_SIZE".into(), max_batch_size.to_string().into())); + } + // If huggingface_hub_cache is some, pass it to the shard // Useful when running inside a docker container if let Some(huggingface_hub_cache) = huggingface_hub_cache { @@ -967,6 +978,7 @@ fn spawn_shards( num_shard: usize, args: &Args, cuda_graphs: Vec, + max_total_tokens: usize, shutdown: Arc, shutdown_receiver: &mpsc::Receiver<()>, shutdown_sender: mpsc::Sender<()>, @@ -998,6 +1010,7 @@ fn spawn_shards( let cuda_memory_fraction = args.cuda_memory_fraction; let rope_scaling = args.rope_scaling; let rope_factor = args.rope_factor; + let max_batch_size = args.max_batch_size; thread::spawn(move || { shard_manager( model_id, @@ -1020,6 +1033,8 @@ fn spawn_shards( cuda_memory_fraction, rope_scaling, rope_factor, + max_total_tokens, + max_batch_size, otlp_endpoint, status_sender, shutdown, @@ -1474,6 +1489,7 @@ fn main() -> Result<(), LauncherError> { num_shard, &args, cuda_graphs, + max_total_tokens, shutdown.clone(), &shutdown_receiver, shutdown_sender, From 45ecf9d04060d2acfbb3286c261b3c5a476ec297 Mon Sep 17 00:00:00 2001 From: "Wang, Yi" Date: Fri, 26 Apr 2024 21:48:58 +0800 Subject: [PATCH 03/22] add intel xpu support for TGI (#1475) # What does this PR do? Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. --------- Signed-off-by: Wang, Yi A Co-authored-by: Morgan Funtowicz Co-authored-by: Nicolas Patry --- .github/workflows/build.yaml | 93 ++++++++++++ Dockerfile_intel | 105 +++++++++++++ launcher/src/env_runtime.rs | 13 +- .../models/cache_manager.py | 6 +- .../custom_modeling/flash_dbrx_modeling.py | 4 +- .../custom_modeling/flash_mixtral_modeling.py | 5 +- .../models/flash_causal_lm.py | 28 +++- .../models/flash_llama.py | 4 + .../models/flash_mistral.py | 6 +- .../models/flash_neox.py | 5 +- .../text_generation_server/models/flash_rw.py | 5 +- .../models/flash_santacoder.py | 4 + .../text_generation_server/models/globals.py | 4 +- server/text_generation_server/utils/dist.py | 9 +- .../utils/flash_attn.py | 142 +++++++++++------- .../utils/import_utils.py | 9 ++ server/text_generation_server/utils/layers.py | 39 ++++- .../utils/paged_attention.py | 30 +++- 18 files changed, 434 insertions(+), 77 deletions(-) create mode 100644 Dockerfile_intel diff --git a/.github/workflows/build.yaml b/.github/workflows/build.yaml index 066ea889..f1131450 100644 --- a/.github/workflows/build.yaml +++ b/.github/workflows/build.yaml @@ -274,12 +274,105 @@ jobs: cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-rocm,mode=min cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-rocm,mode=min + build-and-push-image-intel: + concurrency: + group: ${{ github.workflow }}-build-and-push-image-intel-${{ github.head_ref || github.run_id }} + cancel-in-progress: true + needs: + - start-runner + - build-and-push-image # Wait for the main docker image to be built + - integration-tests # Wait for the main integration-tests + runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner + permissions: + contents: write + packages: write + # This is used to complete the identity challenge + # with sigstore/fulcio when running outside of PRs. + id-token: write + security-events: write + steps: + - name: Checkout repository + uses: actions/checkout@v3 + - name: Initialize Docker Buildx + uses: docker/setup-buildx-action@v2.0.0 + with: + install: true + - name: Inject slug/short variables + uses: rlespinasse/github-slug-action@v4.4.1 + - name: Tailscale + uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966 + with: + authkey: ${{ secrets.TAILSCALE_AUTHKEY }} + - name: Login to GitHub Container Registry + if: github.event_name != 'pull_request' + uses: docker/login-action@v2 + with: + registry: ghcr.io + username: ${{ github.actor }} + password: ${{ secrets.GITHUB_TOKEN }} + - name: Login to internal Container Registry + uses: docker/login-action@v2.1.0 + with: + username: ${{ secrets.TAILSCALE_DOCKER_USERNAME }} + password: ${{ secrets.TAILSCALE_DOCKER_PASSWORD }} + registry: registry.internal.huggingface.tech + - name: Login to Azure Container Registry + if: github.event_name != 'pull_request' + uses: docker/login-action@v2.1.0 + with: + username: ${{ secrets.AZURE_DOCKER_USERNAME }} + password: ${{ secrets.AZURE_DOCKER_PASSWORD }} + registry: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io + # If pull request + - name: Extract metadata (tags, labels) for Docker + if: ${{ github.event_name == 'pull_request' }} + id: meta-pr + uses: docker/metadata-action@v4.3.0 + with: + images: | + registry.internal.huggingface.tech/api-inference/community/text-generation-inference + tags: | + type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-intel + # If main, release or tag + - name: Extract metadata (tags, labels) for Docker + if: ${{ github.event_name != 'pull_request' }} + id: meta + uses: docker/metadata-action@v4.3.0 + with: + flavor: | + latest=false + images: | + registry.internal.huggingface.tech/api-inference/community/text-generation-inference + ghcr.io/huggingface/text-generation-inference + db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference + tags: | + type=semver,pattern={{version}}-intel + type=semver,pattern={{major}}.{{minor}}-intel + type=raw,value=latest-intel,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }} + type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-intel + - name: Build and push Docker image + id: build-and-push + uses: docker/build-push-action@v4 + with: + context: . + file: Dockerfile_intel + push: true + platforms: 'linux/amd64' + build-args: | + GIT_SHA=${{ env.GITHUB_SHA }} + DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}-intel + tags: ${{ steps.meta.outputs.tags || steps.meta-pr.outputs.tags }} + labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }} + cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-intel,mode=min + cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-intel,mode=min + stop-runner: name: Stop self-hosted EC2 runner needs: - start-runner - build-and-push-image - build-and-push-image-rocm + - build-and-push-image-intel - integration-tests runs-on: ubuntu-latest env: diff --git a/Dockerfile_intel b/Dockerfile_intel new file mode 100644 index 00000000..d0791cac --- /dev/null +++ b/Dockerfile_intel @@ -0,0 +1,105 @@ +FROM lukemathwalker/cargo-chef:latest-rust-1.75 AS chef +WORKDIR /usr/src + +ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse + +FROM chef as planner +COPY Cargo.toml Cargo.toml +COPY rust-toolchain.toml rust-toolchain.toml +COPY proto proto +COPY benchmark benchmark +COPY router router +COPY launcher launcher +RUN cargo chef prepare --recipe-path recipe.json + +FROM chef AS builder + +ARG GIT_SHA +ARG DOCKER_LABEL + +RUN PROTOC_ZIP=protoc-21.12-linux-x86_64.zip && \ + curl -OL https://github.com/protocolbuffers/protobuf/releases/download/v21.12/$PROTOC_ZIP && \ + unzip -o $PROTOC_ZIP -d /usr/local bin/protoc && \ + unzip -o $PROTOC_ZIP -d /usr/local 'include/*' && \ + rm -f $PROTOC_ZIP + +COPY --from=planner /usr/src/recipe.json recipe.json +RUN cargo chef cook --release --recipe-path recipe.json + +COPY Cargo.toml Cargo.toml +COPY rust-toolchain.toml rust-toolchain.toml +COPY proto proto +COPY benchmark benchmark +COPY router router +COPY launcher launcher +RUN cargo build --release + + +# Text Generation Inference base image for Intel +FROM intel/intel-extension-for-pytorch:2.1.10-xpu as base + +USER root +# libssl.so.1.1 is not installed on Ubuntu 22.04 by default, install it +RUN wget http://nz2.archive.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2_amd64.deb && \ + dpkg -i ./libssl1.1_1.1.1f-1ubuntu2_amd64.deb + + +RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB \ +| gpg --dearmor | tee /usr/share/keyrings/oneapi-archive-keyring.gpg > /dev/null && echo "deb [signed-by=/usr/share/keyrings/oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main" | tee /etc/apt/sources.list.d/oneAPI.list + +RUN apt-get update && apt install -y intel-basekit xpu-smi cmake python3-dev ninja-build + +# Text Generation Inference base env +ENV HUGGINGFACE_HUB_CACHE=/data \ + HF_HUB_ENABLE_HF_TRANSFER=1 \ + PORT=80 + + +WORKDIR /usr/src +# Build pytorch and ipex +RUN git clone https://github.com/intel/intel-extension-for-pytorch && cd intel-extension-for-pytorch && git checkout -b xpu_main origin/xpu-main +RUN git clone https://github.com/pytorch/pytorch.git && cd pytorch && git checkout 209f2fa8ff86652f67d75c2f19bf9cb9942fd018 && git apply /usr/src/intel-extension-for-pytorch/torch_patches/00*.patch + +# Install server +COPY proto proto +COPY server server +COPY server/Makefile server/Makefile +RUN cd server && \ + make gen-server && \ + pip install -r requirements_cuda.txt && \ + pip install ".[accelerate, peft, outlines]" --no-cache-dir + +ENV CCL_ROOT=/opt/intel/oneapi/ccl/latest +ENV I_MPI_ROOT=/opt/intel/oneapi/mpi/latest +ENV FI_PROVIDER_PATH=/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/lib/prov:/usr/lib/x86_64-linux-gnu/libfabric +ENV DIAGUTIL_PATH=/opt/intel/oneapi/compiler/latest/etc/compiler/sys_check/sys_check.sh +ENV CCL_CONFIGURATION=cpu_gpu_dpcpp +ENV MANPATH=/opt/intel/oneapi/mpi/latest/share/man:/opt/intel/oneapi/mpi/latest/share/man:/opt/intel/oneapi/compiler/latest/share/man +ENV CMAKE_PREFIX_PATH=/opt/intel/oneapi/mkl/latest/lib/cmake:/opt/intel/oneapi/compiler/latest +ENV CMPLR_ROOT=/opt/intel/oneapi/compiler/latest +ENV LIBRARY_PATH=/opt/intel/oneapi/mpi/latest/lib:/opt/intel/oneapi/ccl/latest/lib/:/opt/intel/oneapi/mkl/latest/lib/:/opt/intel/oneapi/compiler/latest/lib +ENV OCL_ICD_FILENAMES=libintelocl_emu.so:libalteracl.so:/opt/intel/oneapi/compiler/latest/lib/libintelocl.so +ENV CLASSPATH=/opt/intel/oneapi/mpi/latest/share/java/mpi.jar:/opt/intel/oneapi/mpi/latest/share/java/mpi.jar +ENV LD_LIBRARY_PATH=/opt/intel/oneapi/ccl/latest/lib/:/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/lib:/opt/intel/oneapi/mpi/latest/lib:/opt/intel/oneapi/mkl/latest/lib:/opt/intel/oneapi/compiler/latest/opt/compiler/lib:/opt/intel/oneapi/compiler/latest/lib:/opt/intel/oneapi/lib:/opt/intel/oneapi/lib/intel64: +ENV MKLROOT=/opt/intel/oneapi/mkl/latest +ENV NLSPATH=/opt/intel/oneapi/mkl/latest/share/locale/%l_%t/%N:/opt/intel/oneapi/compiler/latest/lib/locale/%l_%t/%N +ENV PATH=/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/bin:/opt/intel/oneapi/mpi/latest/bin:/opt/intel/oneapi/mpi/latest/opt/mpi/libfabric/bin:/opt/intel/oneapi/mkl/latest/bin/:/opt/intel/oneapi/compiler/latest/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin +ENV CPATH=/opt/intel/oneapi/mpi/latest/include:/opt/intel/oneapi/ccl/latest/include:/opt/intel/oneapi/mkl/latest/include +ENV CCL_ZE_IPC_EXCHANGE=sockets + + +RUN pip uninstall -y torch && cd pytorch && git submodule update --init --recursive && python setup.py install +RUN pip uninstall -y intel-extension-for-pytorch && cd intel-extension-for-pytorch && git submodule update --init --recursive && USE_AOT_DEVLIST='pvc' BUILD_SEPARATE_OPS=ON BUILD_WITH_CPU=ON USE_XETLA=ON python setup.py install + +# Install benchmarker +COPY --from=builder /usr/src/target/release/text-generation-benchmark /usr/local/bin/text-generation-benchmark +# Install router +COPY --from=builder /usr/src/target/release/text-generation-router /usr/local/bin/text-generation-router +# Install launcher +COPY --from=builder /usr/src/target/release/text-generation-launcher /usr/local/bin/text-generation-launcher + +# Final image +FROM base + +ENTRYPOINT ["text-generation-launcher"] +CMD ["--json-output"] diff --git a/launcher/src/env_runtime.rs b/launcher/src/env_runtime.rs index 9dbc83f7..08fb301c 100644 --- a/launcher/src/env_runtime.rs +++ b/launcher/src/env_runtime.rs @@ -7,14 +7,17 @@ pub(crate) struct Env { git_sha: &'static str, docker_label: &'static str, nvidia_env: String, + xpu_env: String, } impl Env { pub fn new() -> Self { let nvidia_env = nvidia_smi(); + let xpu_env = xpu_smi(); Self { nvidia_env: nvidia_env.unwrap_or("N/A".to_string()), + xpu_env: xpu_env.unwrap_or("N/A".to_string()), cargo_target: env!("VERGEN_CARGO_TARGET_TRIPLE"), cargo_version: env!("VERGEN_RUSTC_SEMVER"), git_sha: option_env!("VERGEN_GIT_SHA").unwrap_or("N/A"), @@ -31,7 +34,8 @@ impl fmt::Display for Env { writeln!(f, "Cargo version: {}", self.cargo_version)?; writeln!(f, "Commit sha: {}", self.git_sha)?; writeln!(f, "Docker label: {}", self.docker_label)?; - write!(f, "nvidia-smi:\n{}", self.nvidia_env)?; + writeln!(f, "nvidia-smi:\n{}", self.nvidia_env)?; + write!(f, "xpu-smi:\n{}", self.xpu_env)?; Ok(()) } @@ -43,3 +47,10 @@ fn nvidia_smi() -> Option { let output = nvidia_smi.replace('\n', "\n "); Some(output.trim().to_string()) } + +fn xpu_smi() -> Option { + let output = Command::new("xpu-smi").arg("discovery").output().ok()?; + let xpu_smi = String::from_utf8(output.stdout).ok()?; + let output = xpu_smi.replace('\n', "\n "); + Some(output.trim().to_string()) +} diff --git a/server/text_generation_server/models/cache_manager.py b/server/text_generation_server/models/cache_manager.py index 85e1b19b..4c65e2dd 100644 --- a/server/text_generation_server/models/cache_manager.py +++ b/server/text_generation_server/models/cache_manager.py @@ -2,6 +2,7 @@ import math import torch from typing import Optional, List, Tuple +from text_generation_server.utils.import_utils import IS_XPU_SYSTEM BLOCK_SIZE: int = 16 # Will be set in warmup @@ -24,7 +25,10 @@ class CacheManager: self.repeat_slots = repeat_slots element_size = torch.tensor([], dtype=dtype).element_size() - x = self.block_size // element_size + if IS_XPU_SYSTEM: + x = 1 + else: + x = self.block_size // element_size self.kv_cache = [ ( diff --git a/server/text_generation_server/models/custom_modeling/flash_dbrx_modeling.py b/server/text_generation_server/models/custom_modeling/flash_dbrx_modeling.py index d04ce39e..d0978bef 100644 --- a/server/text_generation_server/models/custom_modeling/flash_dbrx_modeling.py +++ b/server/text_generation_server/models/custom_modeling/flash_dbrx_modeling.py @@ -21,8 +21,10 @@ from transformers.activations import ACT2FN from transformers.configuration_utils import PretrainedConfig from typing import Optional, List, Tuple, Any from loguru import logger +from text_generation_server.utils.import_utils import IS_XPU_SYSTEM -from vllm.model_executor.layers.fused_moe import fused_moe +if not IS_XPU_SYSTEM: + from vllm.model_executor.layers.fused_moe import fused_moe from text_generation_server.utils import paged_attention, flash_attn from text_generation_server.utils.layers import ( FastLinear, diff --git a/server/text_generation_server/models/custom_modeling/flash_mixtral_modeling.py b/server/text_generation_server/models/custom_modeling/flash_mixtral_modeling.py index be8cb965..3f6c8e03 100644 --- a/server/text_generation_server/models/custom_modeling/flash_mixtral_modeling.py +++ b/server/text_generation_server/models/custom_modeling/flash_mixtral_modeling.py @@ -24,7 +24,10 @@ import torch.distributed import numpy as np from torch import nn -from vllm.model_executor.layers.fused_moe import fused_moe +from text_generation_server.utils.import_utils import IS_XPU_SYSTEM + +if not IS_XPU_SYSTEM: + from vllm.model_executor.layers.fused_moe import fused_moe from transformers.activations import ACT2FN from transformers.configuration_utils import PretrainedConfig from typing import Optional, List, Tuple diff --git a/server/text_generation_server/models/flash_causal_lm.py b/server/text_generation_server/models/flash_causal_lm.py index 1189ccdd..94518b8f 100644 --- a/server/text_generation_server/models/flash_causal_lm.py +++ b/server/text_generation_server/models/flash_causal_lm.py @@ -33,7 +33,7 @@ from text_generation_server.utils import StoppingCriteria, HeterogeneousNextToke from text_generation_server.utils.dist import MEMORY_FRACTION tracer = trace.get_tracer(__name__) - +from text_generation_server.utils.import_utils import IS_CUDA_SYSTEM, IS_ROCM_SYSTEM, IS_XPU_SYSTEM @dataclass class FlashCausalLMBatch(Batch): @@ -752,7 +752,10 @@ class FlashCausalLM(Model): def warmup(self, batch: FlashCausalLMBatch): # The warmup batch is the biggest batch we could ever receive - torch.cuda.empty_cache() + if IS_CUDA_SYSTEM or IS_ROCM_SYSTEM: + torch.cuda.empty_cache() + elif IS_XPU_SYSTEM: + torch.xpu.empty_cache() try: cache_manager = set_cache_manager( batch.blocks, @@ -772,7 +775,10 @@ class FlashCausalLM(Model): f"You need to decrease `--max-batch-prefill-tokens`" ) from e - torch.cuda.synchronize(self.device) + if IS_CUDA_SYSTEM or IS_ROCM_SYSTEM: + torch.cuda.synchronize(self.device) + elif IS_XPU_SYSTEM: + torch.xpu.synchronize(self.device) # Inspired by the original implementation in [vllm](https://github.com/vllm-project/vllm) # Calculate the number of blocks that can be allocated with the free memory @@ -780,12 +786,18 @@ class FlashCausalLM(Model): cache_block_size = BLOCK_SIZE * self.num_kv_heads * self.head_size total_cache_size = self.num_layers * cache_block_size * 2 * dtype_size - total_free_memory, _ = torch.cuda.mem_get_info(self.device) - total_gpu_memory = torch.cuda.get_device_properties(self.device).total_memory + if IS_CUDA_SYSTEM or IS_ROCM_SYSTEM: + total_free_memory, _ = torch.cuda.mem_get_info(self.device) + total_gpu_memory = torch.cuda.get_device_properties(self.device).total_memory - free_memory = max( - 0, total_free_memory - (1 - MEMORY_FRACTION) * total_gpu_memory - ) + free_memory = max( + 0, total_free_memory - (1 - MEMORY_FRACTION) * total_gpu_memory + ) + elif IS_XPU_SYSTEM: + total_gpu_memory = torch.xpu.get_device_properties(self.device).total_memory + free_memory = int(total_gpu_memory *0.5) + else: + raise NotImplementedError("FlashModel is only available on GPU") num_blocks = ( # Leave 5% for some wiggle room diff --git a/server/text_generation_server/models/flash_llama.py b/server/text_generation_server/models/flash_llama.py index f3578f88..f37fc542 100644 --- a/server/text_generation_server/models/flash_llama.py +++ b/server/text_generation_server/models/flash_llama.py @@ -18,6 +18,7 @@ from text_generation_server.utils import ( tracer = trace.get_tracer(__name__) +from text_generation_server.utils.import_utils import IS_XPU_SYSTEM class FlashLlama(FlashCausalLM): def __init__( @@ -33,6 +34,9 @@ class FlashLlama(FlashCausalLM): if torch.cuda.is_available(): device = torch.device(f"cuda:{rank}") dtype = torch.float16 if dtype is None else dtype + elif IS_XPU_SYSTEM: + device = torch.device(f"xpu:{rank}") + dtype = torch.float16 if dtype is None else dtype else: raise NotImplementedError("FlashLlama is only available on GPU") diff --git a/server/text_generation_server/models/flash_mistral.py b/server/text_generation_server/models/flash_mistral.py index 52a30b5f..e2ad78d9 100644 --- a/server/text_generation_server/models/flash_mistral.py +++ b/server/text_generation_server/models/flash_mistral.py @@ -33,8 +33,9 @@ tracer = trace.get_tracer(__name__) # Will be set in init SLIDING_WINDOW: Optional[int] = None SLIDING_WINDOW_BLOCKS: Optional[int] = None +from text_generation_server.utils.import_utils import IS_XPU_SYSTEM -MEM_POOL = torch.cuda.graph_pool_handle() +MEM_POOL = torch.cuda.graph_pool_handle() if torch.cuda.is_available() else None def set_sliding_window(sliding_window: int, sliding_window_blocks: int): @@ -316,6 +317,9 @@ class BaseFlashMistral(FlashCausalLM): if torch.cuda.is_available(): device = torch.device(f"cuda:{rank}") dtype = torch.float16 if dtype is None else dtype + elif IS_XPU_SYSTEM: + device = torch.device(f"xpu:{rank}") + dtype = torch.float16 if dtype is None else dtype else: raise NotImplementedError("FlashMistral is only available on GPU") diff --git a/server/text_generation_server/models/flash_neox.py b/server/text_generation_server/models/flash_neox.py index 5a351bd7..70c978de 100644 --- a/server/text_generation_server/models/flash_neox.py +++ b/server/text_generation_server/models/flash_neox.py @@ -14,7 +14,7 @@ from text_generation_server.utils import ( weight_files, Weights, ) - +from text_generation_server.utils.import_utils import IS_XPU_SYSTEM tracer = trace.get_tracer(__name__) @@ -32,6 +32,9 @@ class FlashNeoXSharded(FlashCausalLM): if torch.cuda.is_available(): device = torch.device(f"cuda:{rank}") dtype = torch.float16 if dtype is None else dtype + elif IS_XPU_SYSTEM: + device = torch.device(f"xpu:{rank}") + dtype = torch.float16 if dtype is None else dtype else: raise NotImplementedError("FlashNeoX is only available on GPU") diff --git a/server/text_generation_server/models/flash_rw.py b/server/text_generation_server/models/flash_rw.py index fc1e26bd..6eb25f22 100644 --- a/server/text_generation_server/models/flash_rw.py +++ b/server/text_generation_server/models/flash_rw.py @@ -15,7 +15,7 @@ from text_generation_server.utils import ( weight_files, Weights, ) - +from text_generation_server.utils.import_utils import IS_XPU_SYSTEM tracer = trace.get_tracer(__name__) @@ -33,6 +33,9 @@ class FlashRWSharded(FlashCausalLM): if torch.cuda.is_available(): device = torch.device(f"cuda:{rank}") dtype = torch.float16 if dtype is None else dtype + elif IS_XPU_SYSTEM: + device = torch.device(f"xpu:{rank}") + dtype = torch.float16 if dtype is None else dtype else: raise NotImplementedError("FlashRW is only available on GPU") diff --git a/server/text_generation_server/models/flash_santacoder.py b/server/text_generation_server/models/flash_santacoder.py index 034949f9..6147398a 100644 --- a/server/text_generation_server/models/flash_santacoder.py +++ b/server/text_generation_server/models/flash_santacoder.py @@ -18,6 +18,7 @@ from text_generation_server.utils import ( Weights, ) +from text_generation_server.utils.import_utils import IS_XPU_SYSTEM tracer = trace.get_tracer(__name__) @@ -35,6 +36,9 @@ class FlashSantacoderSharded(FlashCausalLM): if torch.cuda.is_available(): device = torch.device(f"cuda:{rank}") dtype = torch.float16 if dtype is None else dtype + elif IS_XPU_SYSTEM: + device = torch.device(f"xpu:{rank}") + dtype = torch.float16 if dtype is None else dtype else: raise NotImplementedError("FlashSantacoderSharded is only available on GPU") diff --git a/server/text_generation_server/models/globals.py b/server/text_generation_server/models/globals.py index 91b4225a..b92aa65b 100644 --- a/server/text_generation_server/models/globals.py +++ b/server/text_generation_server/models/globals.py @@ -1,10 +1,10 @@ import torch import os -MEM_POOL = torch.cuda.graph_pool_handle() +MEM_POOL = torch.cuda.graph_pool_handle() if torch.cuda.is_available() else None # This is overridden by the cli cuda_graphs = os.getenv("CUDA_GRAPHS") -if cuda_graphs is not None and cuda_graphs != "0": +if torch.cuda.is_available() and cuda_graphs is not None and cuda_graphs != "0": try: cuda_graphs = [int(item) for item in cuda_graphs.split(",")] except Exception as e: diff --git a/server/text_generation_server/utils/dist.py b/server/text_generation_server/utils/dist.py index d02bfc5b..3625e6f2 100644 --- a/server/text_generation_server/utils/dist.py +++ b/server/text_generation_server/utils/dist.py @@ -57,7 +57,14 @@ def initialize_torch_distributed(): options.is_high_priority_stream = True options._timeout = timedelta(seconds=60) else: - backend = "gloo" + try: + import oneccl_bindings_for_pytorch + + backend = "ccl" + if os.getenv("CCL_WORKER_COUNT", None) is None: + os.environ["CCL_WORKER_COUNT"] = str(1) + except ImportError: + backend = "gloo" options = None if WORLD_SIZE == 1: diff --git a/server/text_generation_server/utils/flash_attn.py b/server/text_generation_server/utils/flash_attn.py index 45090c64..583a8f91 100644 --- a/server/text_generation_server/utils/flash_attn.py +++ b/server/text_generation_server/utils/flash_attn.py @@ -2,69 +2,81 @@ import os import torch from loguru import logger +import math -from text_generation_server.utils.import_utils import IS_CUDA_SYSTEM, IS_ROCM_SYSTEM +from text_generation_server.utils.import_utils import ( + IS_CUDA_SYSTEM, + IS_ROCM_SYSTEM, + IS_XPU_SYSTEM, +) if os.getenv("USE_FLASH_ATTENTION", "").lower() == "false": raise ImportError("`USE_FLASH_ATTENTION` is false.") - -if not torch.cuda.is_available(): - raise ImportError("CUDA is not available") - -major, minor = torch.cuda.get_device_capability() -is_sm75 = major == 7 and minor == 5 -is_sm8x = major == 8 and minor >= 0 -is_sm90 = major == 9 and minor == 0 - -HAS_FLASH_ATTN = False +HAS_FLASH_ATTN = True HAS_FLASH_ATTN_V2_CUDA = False HAS_FLASH_ATTN_V2_ROCM = False -try: + +if IS_XPU_SYSTEM: + import intel_extension_for_pytorch as ipex + +if IS_CUDA_SYSTEM or IS_ROCM_SYSTEM: + if not torch.cuda.is_available(): + raise ImportError("CUDA is not available") + + major, minor = torch.cuda.get_device_capability() + is_sm75 = major == 7 and minor == 5 + is_sm8x = major == 8 and minor >= 0 + is_sm90 = major == 9 and minor == 0 + + HAS_FLASH_ATTN = False + HAS_FLASH_ATTN_V2_CUDA = False + HAS_FLASH_ATTN_V2_ROCM = False try: - import flash_attn_2_cuda - except ImportError: - architecture_suffix = "" - if IS_CUDA_SYSTEM: - architecture_suffix = "-cuda" + try: + import flash_attn_2_cuda + except ImportError: + architecture_suffix = "" + if IS_CUDA_SYSTEM: + architecture_suffix = "-cuda" + elif IS_ROCM_SYSTEM: + architecture_suffix = "-rocm" + raise ImportError( + "Flash Attention V2 is not installed.\n" + "Use the official Docker image (ghcr.io/huggingface/text-generation-inference:latest) " + f"or install flash attention v2 with `cd server && make install install-flash-attention-v2{architecture_suffix}`" + ) + if not (is_sm8x or is_sm90): + raise ImportError( + f"GPU with CUDA capability {major} {minor} is not supported for " + "Flash Attention V2" + ) + HAS_FLASH_ATTN_V2_CUDA = IS_CUDA_SYSTEM + HAS_FLASH_ATTN_V2_ROCM = IS_ROCM_SYSTEM + except ImportError as e: + try: + import flash_attn_cuda + except ImportError: + raise ImportError( + "Flash Attention is not installed.\n" + "Use the official Docker image (ghcr.io/huggingface/text-generation-inference:latest) " + "or install flash attention with `cd server && make install install-flash-attention`" + ) from e + + if IS_CUDA_SYSTEM and not (is_sm75 or is_sm8x or is_sm90): + raise ImportError( + f"GPU with CUDA capability {major} {minor} is not supported" + ) from e elif IS_ROCM_SYSTEM: - architecture_suffix = "-rocm" - raise ImportError( - "Flash Attention V2 is not installed.\n" - "Use the official Docker image (ghcr.io/huggingface/text-generation-inference:latest) " - f"or install flash attention v2 with `cd server && make install install-flash-attention-v2{architecture_suffix}`" - ) - if not (is_sm8x or is_sm90): - raise ImportError( - f"GPU with CUDA capability {major} {minor} is not supported for " - "Flash Attention V2" - ) - HAS_FLASH_ATTN_V2_CUDA = IS_CUDA_SYSTEM - HAS_FLASH_ATTN_V2_ROCM = IS_ROCM_SYSTEM -except ImportError as e: - try: - import flash_attn_cuda - except ImportError: - raise ImportError( - "Flash Attention is not installed.\n" - "Use the official Docker image (ghcr.io/huggingface/text-generation-inference:latest) " - "or install flash attention with `cd server && make install install-flash-attention`" - ) from e + for idx in range(torch.cuda.device_count()): + if "MI210" not in torch.cuda.get_device_name( + idx + ) and "MI250" not in torch.cuda.get_device_name(idx): + raise ImportError( + f"AMD GPU {torch.cuda.get_device_name(idx)} does not support flash-attention" + ) - if IS_CUDA_SYSTEM and not (is_sm75 or is_sm8x or is_sm90): - raise ImportError( - f"GPU with CUDA capability {major} {minor} is not supported" - ) from e - elif IS_ROCM_SYSTEM: - for idx in range(torch.cuda.device_count()): - if "MI210" not in torch.cuda.get_device_name( - idx - ) and "MI250" not in torch.cuda.get_device_name(idx): - raise ImportError( - f"AMD GPU {torch.cuda.get_device_name(idx)} does not support flash-attention" - ) - - logger.warning(f"Unable to use Flash Attention V2: {e}") - HAS_FLASH_ATTN = True + logger.warning(f"Unable to use Flash Attention V2: {e}") + HAS_FLASH_ATTN = True def attention( @@ -80,6 +92,28 @@ def attention( if window_size_left <= 0 and window_size_left != -1: raise ValueError("`window_size_left` must be > 0 or -1") + if IS_XPU_SYSTEM: + if window_size_left != -1: + raise ValueError( + f"XPU version of Flash Attention does not support window attention (window_size_left != -1, got window_size_left={window_size_left})." + ) + return ipex.llm.functional.varlen_attention( + q, + k, + v, + out, + cu_seqlens, + cu_seqlens, + max_s, + max_s, + 0.0, + softmax_scale, + False, + True, + False, + None, + ) + if HAS_FLASH_ATTN_V2_CUDA: return flash_attn_2_cuda.varlen_fwd( q, diff --git a/server/text_generation_server/utils/import_utils.py b/server/text_generation_server/utils/import_utils.py index 428c9f3e..7c0d8001 100644 --- a/server/text_generation_server/utils/import_utils.py +++ b/server/text_generation_server/utils/import_utils.py @@ -1,4 +1,13 @@ import torch +def is_xpu_available(): + try: + import intel_extension_for_pytorch + except ImportError: + return False + + return hasattr(torch, "xpu") and torch.xpu.is_available() + IS_ROCM_SYSTEM = torch.version.hip is not None IS_CUDA_SYSTEM = torch.version.cuda is not None +IS_XPU_SYSTEM = is_xpu_available() diff --git a/server/text_generation_server/utils/layers.py b/server/text_generation_server/utils/layers.py index 69bd5e88..638cb0a0 100644 --- a/server/text_generation_server/utils/layers.py +++ b/server/text_generation_server/utils/layers.py @@ -18,7 +18,14 @@ except ImportError: from accelerate import init_empty_weights from text_generation_server.utils.gptq.quant_linear import QuantLinear -from text_generation_server.utils.import_utils import IS_CUDA_SYSTEM, IS_ROCM_SYSTEM +from text_generation_server.utils.import_utils import ( + IS_CUDA_SYSTEM, + IS_ROCM_SYSTEM, + IS_XPU_SYSTEM, +) + +if IS_XPU_SYSTEM: + import intel_extension_for_pytorch as ipex HAS_AWQ = True try: @@ -812,7 +819,15 @@ try: class FastLayerNorm(nn.LayerNorm): def forward(self, hidden_states, residual=None): - if hidden_states.shape[-1] > 8192 or IS_ROCM_SYSTEM: + if IS_XPU_SYSTEM: + res_out = hidden_states + out = ipex.llm.functional.add_layer_norm( + residual, hidden_states, self.weight, self.bias, self.eps, True + ) + if residual is not None: + res_out = residual + return out, res_out + elif hidden_states.shape[-1] > 8192 or IS_ROCM_SYSTEM: if residual is not None: hidden_states += residual residual = hidden_states @@ -858,7 +873,20 @@ try: return cls(weight, eps) def forward(self, hidden_states, residual=None): - if hidden_states.shape[-1] > 8192: + if IS_XPU_SYSTEM: + residual_out = hidden_states + out = ipex.llm.functional.add_rms_norm( + residual, + hidden_states, + self.weight, + None, + self.variance_epsilon, + True, + ) + if residual is not None: + residual_out = residual + return out, residual_out + elif hidden_states.shape[-1] > 8192: if residual is not None: hidden_states += residual residual = hidden_states @@ -984,6 +1012,10 @@ try: # Inplace operation, updating query and key. pos_encoding_ops.rotary_embedding(query, key, head_size, cos, sin, True) + elif IS_XPU_SYSTEM: + ipex.llm.functional.rotary_embedding( + query, key, sin, cos, query.size(-1), True + ) else: raise ValueError( "Your system seem to be not supported. Please check your install or open an issue at https://github.com/huggingface/text-generation-inference/issues with a clear reproduction." @@ -1103,6 +1135,7 @@ try: cos = torch.index_select(self._cos_cached, 0, position_ids) sin = torch.index_select(self._sin_cached, 0, position_ids) + # Note: this unsqueeze is not necessary on RoCm + VLLM ROPE implementation, but we leave it as is to avoid yet an other controlflow. return cos.unsqueeze(1), sin.unsqueeze(1) diff --git a/server/text_generation_server/utils/paged_attention.py b/server/text_generation_server/utils/paged_attention.py index 487a3a72..62c0c893 100644 --- a/server/text_generation_server/utils/paged_attention.py +++ b/server/text_generation_server/utils/paged_attention.py @@ -1,9 +1,15 @@ import torch - -from text_generation_server.utils.import_utils import IS_CUDA_SYSTEM, IS_ROCM_SYSTEM +from text_generation_server.utils.import_utils import ( + IS_CUDA_SYSTEM, + IS_ROCM_SYSTEM, + IS_XPU_SYSTEM, +) _PARTITION_SIZE = 512 +if IS_XPU_SYSTEM: + import intel_extension_for_pytorch as ipex + def reshape_and_cache( key: torch.Tensor, @@ -22,6 +28,10 @@ def reshape_and_cache( from vllm import cache_ops cache_ops.reshape_and_cache(key, value, key_cache, value_cache, slots) + elif IS_XPU_SYSTEM: + ipex.llm.modules.PagedAttention.reshape_and_cache( + key, value, key_cache, value_cache, slots + ) else: raise ValueError("vllm is not supported on your system") @@ -58,6 +68,22 @@ def attention( block_size = value_cache.shape[3] num_seqs, num_heads, head_size = query.shape max_num_partitions = (max_s + _PARTITION_SIZE - 1) // _PARTITION_SIZE + if IS_XPU_SYSTEM: + query = query.contiguous() + return ipex.llm.modules.PagedAttention.single_query_cached_kv_attention( + out, + query, + key_cache, + value_cache, + kv_head_mapping, + softmax_scale, + block_tables, + input_lengths, + block_size, + max_s, + None, + ) + # NOTE(woosuk): We use a simple heuristic to decide whether to use # PagedAttention V1 or V2. If the number of partitions is 1, we use # V1 to avoid the overhead of reduction. Also, if the number of From a8fd4236eb3421c0c9e8845de5cd8183e9793ef2 Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Fri, 26 Apr 2024 15:51:09 +0200 Subject: [PATCH 04/22] Blunder (#1815) # What does this PR do? Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. --- .../models/flash_mistral.py | 39 ++++++------------- 1 file changed, 12 insertions(+), 27 deletions(-) diff --git a/server/text_generation_server/models/flash_mistral.py b/server/text_generation_server/models/flash_mistral.py index e2ad78d9..6959e2ec 100644 --- a/server/text_generation_server/models/flash_mistral.py +++ b/server/text_generation_server/models/flash_mistral.py @@ -515,33 +515,18 @@ class BaseFlashMistral(FlashCausalLM): cuda_graph = self.cuda_graphs.get(padded_bs, None) if cu_seqlen_prefill is not None or cuda_graph is None: - - if cu_seqlen_prefill is None: - logits, speculative_logits = self.compiled_model( - input_ids=input_ids, - position_ids=position_ids, - cu_seqlen_prefill=cu_seqlen_prefill, - kv_cache=kv_cache, - block_tables=block_tables, - slots=slots, - input_lengths=input_lengths, - max_s=max_s, - prefill_cache_indices=batch.prefill_cache_indices, - lm_head_indices=lm_head_indices, - ) - else: - logits, speculative_logits = self.model.forward( - input_ids=input_ids, - position_ids=position_ids, - cu_seqlen_prefill=cu_seqlen_prefill, - kv_cache=kv_cache, - block_tables=block_tables, - slots=slots, - input_lengths=input_lengths, - max_s=max_s, - prefill_cache_indices=batch.prefill_cache_indices, - lm_head_indices=lm_head_indices, - ) + logits, speculative_logits = self.model.forward( + input_ids=input_ids, + position_ids=position_ids, + cu_seqlen_prefill=cu_seqlen_prefill, + kv_cache=kv_cache, + block_tables=block_tables, + slots=slots, + input_lengths=input_lengths, + max_s=max_s, + prefill_cache_indices=batch.prefill_cache_indices, + lm_head_indices=lm_head_indices, + ) if batch.prefill_cache_indices is not None: batch.prefill_cache_indices = None return logits, speculative_logits From 8b8e8f663286b8a5f4d5c5fb14cd02a60cb43652 Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Fri, 26 Apr 2024 19:19:08 +0200 Subject: [PATCH 05/22] Fixing qwen2. (#1818) # What does this PR do? Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. --- server/text_generation_server/models/flash_qwen2.py | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/server/text_generation_server/models/flash_qwen2.py b/server/text_generation_server/models/flash_qwen2.py index c3c63516..cb3cf6b0 100644 --- a/server/text_generation_server/models/flash_qwen2.py +++ b/server/text_generation_server/models/flash_qwen2.py @@ -4,7 +4,7 @@ import torch import torch.distributed from opentelemetry import trace -from transformers.models.qwen2 import Qwen2Tokenizer +from transformers import AutoTokenizer, AutoConfig from typing import Optional from text_generation_server.models.cache_manager import BLOCK_SIZE @@ -15,7 +15,6 @@ from text_generation_server.models.flash_mistral import ( from text_generation_server.models.custom_modeling.flash_qwen2_modeling import ( Qwen2ForCausalLM, ) -from transformers.models.qwen2 import Qwen2Config from text_generation_server.utils import ( initialize_torch_distributed, weight_files, @@ -42,7 +41,7 @@ class FlashQwen2(BaseFlashMistral): else: raise NotImplementedError("FlashQwen2 is only available on GPU") - tokenizer = Qwen2Tokenizer.from_pretrained( + tokenizer = AutoTokenizer.from_pretrained( model_id, revision=revision, padding_side="left", @@ -50,7 +49,7 @@ class FlashQwen2(BaseFlashMistral): trust_remote_code=trust_remote_code, ) - config = Qwen2Config.from_pretrained( + config = AutoConfig.from_pretrained( model_id, revision=revision, trust_remote_code=trust_remote_code ) config.quantize = quantize From e9f03f822a766f071620457bd977f7987e65b20e Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Fri, 26 Apr 2024 19:19:55 +0200 Subject: [PATCH 06/22] Dummy CI run. (#1817) # What does this PR do? Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. --- .../models/flash_causal_lm.py | 13 ++++++++++--- server/text_generation_server/models/flash_llama.py | 1 + server/text_generation_server/models/flash_neox.py | 1 + server/text_generation_server/models/flash_rw.py | 1 + .../models/flash_santacoder.py | 1 + server/text_generation_server/utils/import_utils.py | 2 ++ server/text_generation_server/utils/layers.py | 1 + 7 files changed, 17 insertions(+), 3 deletions(-) diff --git a/server/text_generation_server/models/flash_causal_lm.py b/server/text_generation_server/models/flash_causal_lm.py index 94518b8f..a6d0204f 100644 --- a/server/text_generation_server/models/flash_causal_lm.py +++ b/server/text_generation_server/models/flash_causal_lm.py @@ -33,7 +33,12 @@ from text_generation_server.utils import StoppingCriteria, HeterogeneousNextToke from text_generation_server.utils.dist import MEMORY_FRACTION tracer = trace.get_tracer(__name__) -from text_generation_server.utils.import_utils import IS_CUDA_SYSTEM, IS_ROCM_SYSTEM, IS_XPU_SYSTEM +from text_generation_server.utils.import_utils import ( + IS_CUDA_SYSTEM, + IS_ROCM_SYSTEM, + IS_XPU_SYSTEM, +) + @dataclass class FlashCausalLMBatch(Batch): @@ -788,14 +793,16 @@ class FlashCausalLM(Model): if IS_CUDA_SYSTEM or IS_ROCM_SYSTEM: total_free_memory, _ = torch.cuda.mem_get_info(self.device) - total_gpu_memory = torch.cuda.get_device_properties(self.device).total_memory + total_gpu_memory = torch.cuda.get_device_properties( + self.device + ).total_memory free_memory = max( 0, total_free_memory - (1 - MEMORY_FRACTION) * total_gpu_memory ) elif IS_XPU_SYSTEM: total_gpu_memory = torch.xpu.get_device_properties(self.device).total_memory - free_memory = int(total_gpu_memory *0.5) + free_memory = int(total_gpu_memory * 0.5) else: raise NotImplementedError("FlashModel is only available on GPU") diff --git a/server/text_generation_server/models/flash_llama.py b/server/text_generation_server/models/flash_llama.py index f37fc542..609a188d 100644 --- a/server/text_generation_server/models/flash_llama.py +++ b/server/text_generation_server/models/flash_llama.py @@ -20,6 +20,7 @@ tracer = trace.get_tracer(__name__) from text_generation_server.utils.import_utils import IS_XPU_SYSTEM + class FlashLlama(FlashCausalLM): def __init__( self, diff --git a/server/text_generation_server/models/flash_neox.py b/server/text_generation_server/models/flash_neox.py index 70c978de..f82e27db 100644 --- a/server/text_generation_server/models/flash_neox.py +++ b/server/text_generation_server/models/flash_neox.py @@ -15,6 +15,7 @@ from text_generation_server.utils import ( Weights, ) from text_generation_server.utils.import_utils import IS_XPU_SYSTEM + tracer = trace.get_tracer(__name__) diff --git a/server/text_generation_server/models/flash_rw.py b/server/text_generation_server/models/flash_rw.py index 6eb25f22..ccf38a0c 100644 --- a/server/text_generation_server/models/flash_rw.py +++ b/server/text_generation_server/models/flash_rw.py @@ -16,6 +16,7 @@ from text_generation_server.utils import ( Weights, ) from text_generation_server.utils.import_utils import IS_XPU_SYSTEM + tracer = trace.get_tracer(__name__) diff --git a/server/text_generation_server/models/flash_santacoder.py b/server/text_generation_server/models/flash_santacoder.py index 6147398a..e66f1bf8 100644 --- a/server/text_generation_server/models/flash_santacoder.py +++ b/server/text_generation_server/models/flash_santacoder.py @@ -19,6 +19,7 @@ from text_generation_server.utils import ( ) from text_generation_server.utils.import_utils import IS_XPU_SYSTEM + tracer = trace.get_tracer(__name__) diff --git a/server/text_generation_server/utils/import_utils.py b/server/text_generation_server/utils/import_utils.py index 7c0d8001..db205f4d 100644 --- a/server/text_generation_server/utils/import_utils.py +++ b/server/text_generation_server/utils/import_utils.py @@ -1,5 +1,6 @@ import torch + def is_xpu_available(): try: import intel_extension_for_pytorch @@ -8,6 +9,7 @@ def is_xpu_available(): return hasattr(torch, "xpu") and torch.xpu.is_available() + IS_ROCM_SYSTEM = torch.version.hip is not None IS_CUDA_SYSTEM = torch.version.cuda is not None IS_XPU_SYSTEM = is_xpu_available() diff --git a/server/text_generation_server/utils/layers.py b/server/text_generation_server/utils/layers.py index 638cb0a0..8c46ea49 100644 --- a/server/text_generation_server/utils/layers.py +++ b/server/text_generation_server/utils/layers.py @@ -8,6 +8,7 @@ from typing import List, Tuple, Optional from loguru import logger from functools import lru_cache +# Dummy comment. HAS_BITS_AND_BYTES = True try: import bitsandbytes as bnb From 007d5e54aa76be74925501011fa8029bc5034f89 Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Sun, 28 Apr 2024 17:54:19 +0200 Subject: [PATCH 07/22] Changing the waiting_served_ratio default (stack more aggressively by default). (#1820) # What does this PR do? This should enable more aggressive by default stacking, meaning better throughput (in throughput constrained environements). Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. --- docs/source/basic_tutorials/launcher.md | 2 +- launcher/src/main.rs | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/source/basic_tutorials/launcher.md b/docs/source/basic_tutorials/launcher.md index de7c995d..1e5b6fd2 100644 --- a/docs/source/basic_tutorials/launcher.md +++ b/docs/source/basic_tutorials/launcher.md @@ -162,7 +162,7 @@ Options: This setting is only applied if there is room in the batch as defined by `max_batch_total_tokens`. [env: WAITING_SERVED_RATIO=] - [default: 1.2] + [default: 0.3] ``` ## MAX_BATCH_PREFILL_TOKENS diff --git a/launcher/src/main.rs b/launcher/src/main.rs index f264e000..28226fb4 100644 --- a/launcher/src/main.rs +++ b/launcher/src/main.rs @@ -251,7 +251,7 @@ struct Args { /// /// This setting is only applied if there is room in the batch /// as defined by `max_batch_total_tokens`. - #[clap(default_value = "1.2", long, env)] + #[clap(default_value = "0.3", long, env)] waiting_served_ratio: f32, /// Limits the number of tokens for the prefill operation. From eade7377140a680a79bd2ce3f2d486314cf5a9b9 Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Mon, 29 Apr 2024 17:23:40 +0200 Subject: [PATCH 08/22] Better graceful shutdown. (#1827) # What does this PR do? Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. --- launcher/src/main.rs | 6 +----- server/text_generation_server/server.py | 23 ++++++++++++++++++----- 2 files changed, 19 insertions(+), 10 deletions(-) diff --git a/launcher/src/main.rs b/launcher/src/main.rs index 28226fb4..ca6aa8dd 100644 --- a/launcher/src/main.rs +++ b/launcher/src/main.rs @@ -683,9 +683,7 @@ fn shard_manager( // We received a shutdown signal if shutdown.load(Ordering::SeqCst) { - p.kill().unwrap(); - let _ = p.wait(); - tracing::info!("Shard terminated"); + terminate("shard", p, Duration::from_secs(90)).unwrap(); return; } @@ -1245,7 +1243,6 @@ fn terminate(process_name: &str, mut process: Child, timeout: Duration) -> io::R signal::kill(Pid::from_raw(process.id() as i32), Signal::SIGTERM).unwrap(); tracing::info!("Waiting for {process_name} to gracefully shutdown"); - while terminate_time.elapsed() < timeout { if let Some(status) = process.try_wait()? { tracing::info!("{process_name} terminated"); @@ -1253,7 +1250,6 @@ fn terminate(process_name: &str, mut process: Child, timeout: Duration) -> io::R } sleep(Duration::from_millis(100)); } - tracing::info!("Killing {process_name}"); process.kill()?; diff --git a/server/text_generation_server/server.py b/server/text_generation_server/server.py index 495c2c0c..158966e3 100644 --- a/server/text_generation_server/server.py +++ b/server/text_generation_server/server.py @@ -2,6 +2,7 @@ import asyncio import os import torch import time +import signal from grpc import aio from loguru import logger @@ -19,6 +20,21 @@ from text_generation_server.tracing import UDSOpenTelemetryAioServerInterceptor from text_generation_server.models.idefics_causal_lm import IdeficsCausalLMBatch +class SignalHandler: + KEEP_PROCESSING = True + + def __init__(self): + signal.signal(signal.SIGINT, self.exit_gracefully) + signal.signal(signal.SIGTERM, self.exit_gracefully) + + def exit_gracefully(self, signum, frame): + print(f"Exiting gracefully: Signal {signum}") + self.KEEP_PROCESSING = False + + +signal_handler = SignalHandler() + + class TextGenerationService(generate_pb2_grpc.TextGenerationServiceServicer): def __init__( self, @@ -231,11 +247,8 @@ def serve( logger.info("Server started at {}".format(local_url)) - try: - await server.wait_for_termination() - except KeyboardInterrupt: - logger.info("Signal received. Shutting down") - await server.stop(0) + while signal_handler.KEEP_PROCESSING: + await asyncio.sleep(0.5) asyncio.run( serve_inner( From f75c1a5b264f5ec6b2e5e1b29a2070e6193cdf6d Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Tue, 30 Apr 2024 10:52:37 +0200 Subject: [PATCH 09/22] Prepare release. --- Cargo.toml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Cargo.toml b/Cargo.toml index 593fd950..34e55652 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -9,7 +9,7 @@ members = [ resolver = "2" [workspace.package] -version = "2.0.1" +version = "2.0.2" edition = "2021" authors = ["Olivier Dehaene"] homepage = "https://github.com/huggingface/text-generation-inference" From 51ee60da74700d051a2b35ca236be53dac0caea2 Mon Sep 17 00:00:00 2001 From: Maziyar Panahi Date: Tue, 30 Apr 2024 11:07:17 +0200 Subject: [PATCH 10/22] Add the missing `tool_prompt` parameter to Python client (#1825) # What does this PR do? This PR adds the missing `tool_prompt` parameter in Python client ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [x] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [x] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. @Narsil --- clients/python/text_generation/client.py | 8 ++++++++ clients/python/text_generation/types.py | 2 ++ 2 files changed, 10 insertions(+) diff --git a/clients/python/text_generation/client.py b/clients/python/text_generation/client.py index 95d23901..0e86901d 100644 --- a/clients/python/text_generation/client.py +++ b/clients/python/text_generation/client.py @@ -80,6 +80,7 @@ class Client: temperature: Optional[float] = None, top_p: Optional[float] = None, tools: Optional[List[Tool]] = None, + tool_prompt: Optional[str] = None, tool_choice: Optional[str] = None, ): """ @@ -119,6 +120,8 @@ class Client: higher are kept for generation tools (`List[Tool]`): List of tools to use + tool_prompt (`str`): + A prompt to be appended before the tools tool_choice (`str`): The tool to use @@ -139,6 +142,7 @@ class Client: temperature=temperature, top_p=top_p, tools=tools, + tool_prompt=tool_prompt, tool_choice=tool_choice, ) if not stream: @@ -466,6 +470,7 @@ class AsyncClient: temperature: Optional[float] = None, top_p: Optional[float] = None, tools: Optional[List[Tool]] = None, + tool_prompt: Optional[str] = None, tool_choice: Optional[str] = None, ) -> Union[ChatComplete, AsyncIterator[ChatCompletionChunk]]: """ @@ -505,6 +510,8 @@ class AsyncClient: higher are kept for generation tools (`List[Tool]`): List of tools to use + tool_prompt (`str`): + A prompt to be appended before the tools tool_choice (`str`): The tool to use @@ -525,6 +532,7 @@ class AsyncClient: temperature=temperature, top_p=top_p, tools=tools, + tool_prompt=tool_prompt, tool_choice=tool_choice, ) if not stream: diff --git a/clients/python/text_generation/types.py b/clients/python/text_generation/types.py index cfa2a9ed..5e32bc6f 100644 --- a/clients/python/text_generation/types.py +++ b/clients/python/text_generation/types.py @@ -159,6 +159,8 @@ class ChatRequest(BaseModel): top_p: Optional[float] = None # List of tools to be used tools: Optional[List[Tool]] = None + # A prompt to be appended before the tools + tool_prompt: Optional[str] = None # Choice of tool to be used tool_choice: Optional[str] = None From 04d4765bad5707458955189fbf39e8b485de5cbd Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Tue, 30 Apr 2024 11:39:38 +0200 Subject: [PATCH 11/22] Small CI cleanup. (#1801) # What does this PR do? Just unifying some branches and making intentions clearer (no cuda graph when 0 all the way in the launcher) Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. --- launcher/src/main.rs | 12 ++++++++---- server/text_generation_server/models/globals.py | 2 +- 2 files changed, 9 insertions(+), 5 deletions(-) diff --git a/launcher/src/main.rs b/launcher/src/main.rs index ca6aa8dd..23944f40 100644 --- a/launcher/src/main.rs +++ b/launcher/src/main.rs @@ -1284,7 +1284,7 @@ fn main() -> Result<(), LauncherError> { tracing::info!("{}", env_runtime); } - tracing::info!("{:?}", args); + tracing::info!("{:#?}", args); let get_max_position_embeddings = || -> Result> { let model_id = args.model_id.clone(); @@ -1317,7 +1317,12 @@ fn main() -> Result<(), LauncherError> { (Some(max_position_embeddings), _) | (None, Some(max_position_embeddings)) => { if max_position_embeddings > max_default { let max = max_position_embeddings; - tracing::info!("Model supports up to {max} but tgi will now set its default to {max_default} instead. This is to save VRAM by refusing large prompts in order to allow more users on the same hardware. You can increase that size using `--max-batch-prefill-tokens={} --max-total-tokens={max} --max-input-tokens={}`.", max + 50, max - 1); + if args.max_input_tokens.is_none() + && args.max_total_tokens.is_none() + && args.max_batch_prefill_tokens.is_none() + { + tracing::info!("Model supports up to {max} but tgi will now set its default to {max_default} instead. This is to save VRAM by refusing large prompts in order to allow more users on the same hardware. You can increase that size using `--max-batch-prefill-tokens={} --max-total-tokens={max} --max-input-tokens={}`.", max + 50, max - 1); + } max_default } else { max_position_embeddings @@ -1389,8 +1394,7 @@ fn main() -> Result<(), LauncherError> { } let cuda_graphs = match (&args.cuda_graphs, &args.quantize) { - (Some(cuda_graphs), Some(_q)) => cuda_graphs.clone(), - (Some(cuda_graphs), None) => cuda_graphs.clone(), + (Some(cuda_graphs), _) => cuda_graphs.iter().cloned().filter(|&c| c > 0).collect(), #[allow(deprecated)] ( None, diff --git a/server/text_generation_server/models/globals.py b/server/text_generation_server/models/globals.py index b92aa65b..6f8d1017 100644 --- a/server/text_generation_server/models/globals.py +++ b/server/text_generation_server/models/globals.py @@ -4,7 +4,7 @@ import os MEM_POOL = torch.cuda.graph_pool_handle() if torch.cuda.is_available() else None # This is overridden by the cli cuda_graphs = os.getenv("CUDA_GRAPHS") -if torch.cuda.is_available() and cuda_graphs is not None and cuda_graphs != "0": +if cuda_graphs is not None: try: cuda_graphs = [int(item) for item in cuda_graphs.split(",")] except Exception as e: From 743ecbca3aa5a708f438ae473f17ede3c15452b6 Mon Sep 17 00:00:00 2001 From: Brandon Royal <2762697+brandonroyal@users.noreply.github.com> Date: Tue, 30 Apr 2024 05:39:52 -0400 Subject: [PATCH 12/22] Add reference to TPU support (#1760) # What does this PR do? This PR makes a small addition to the readme that reference new TGI support for TPUs via Optimum TPU (https://huggingface.co/docs/optimum-tpu/howto/serving) --- README.md | 1 + 1 file changed, 1 insertion(+) diff --git a/README.md b/README.md index ad66e328..74616748 100644 --- a/README.md +++ b/README.md @@ -64,6 +64,7 @@ Text Generation Inference (TGI) is a toolkit for deploying and serving Large Lan - [Inferentia](https://github.com/huggingface/optimum-neuron/tree/main/text-generation-inference) - [Intel GPU](https://github.com/huggingface/text-generation-inference/pull/1475) - [Gaudi](https://github.com/huggingface/tgi-gaudi) +- [Google TPU](https://huggingface.co/docs/optimum-tpu/howto/serving) ## Get Started From 8332fc490804a83d3ac050bc825f3175c4b7fc51 Mon Sep 17 00:00:00 2001 From: OlivierDehaene Date: Tue, 30 Apr 2024 11:45:26 +0200 Subject: [PATCH 13/22] fix: use get_speculate to the number of layers (#1737) --- server/text_generation_server/utils/layers.py | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/server/text_generation_server/utils/layers.py b/server/text_generation_server/utils/layers.py index 8c46ea49..6e4a13cd 100644 --- a/server/text_generation_server/utils/layers.py +++ b/server/text_generation_server/utils/layers.py @@ -8,7 +8,8 @@ from typing import List, Tuple, Optional from loguru import logger from functools import lru_cache -# Dummy comment. +from text_generation_server.utils.speculate import get_speculate + HAS_BITS_AND_BYTES = True try: import bitsandbytes as bnb @@ -445,7 +446,7 @@ class MedusaModel(torch.nn.Module): self.heads = torch.nn.ModuleList( [ MedusaHead(config, medusa_config, prefix=f"{i}", weights=weights) - for i in range(medusa_config["medusa_num_heads"]) + for i in range(get_speculate()) ] ) @@ -542,7 +543,7 @@ class MedusaHeadV2(nn.Module): ) routing[k] = filename - self.n_medusa_heads = medusa_config["medusa_num_heads"] + self.n_medusa_heads = get_speculate() assert medusa_config["medusa_num_layers"] == 1 self.linear = TensorParallelColumnLinear.load_multi( From f6615080b9290a89d9e83d29257d510c8c994762 Mon Sep 17 00:00:00 2001 From: drbh Date: Tue, 30 Apr 2024 05:45:49 -0400 Subject: [PATCH 14/22] feat: add how it works section (#1773) This PR adds a short "how it works" section to guidance and includes a mention to the outlines library that enables grammars/tools *and a small formatting change --------- Co-authored-by: Mishig --- docs/source/conceptual/guidance.md | 108 +++++++++++++++-------------- 1 file changed, 56 insertions(+), 52 deletions(-) diff --git a/docs/source/conceptual/guidance.md b/docs/source/conceptual/guidance.md index cecb3f03..d3ec5fb9 100644 --- a/docs/source/conceptual/guidance.md +++ b/docs/source/conceptual/guidance.md @@ -12,6 +12,10 @@ Before we jump into the deep end, ensure your system is using TGI version `1.4.3 If you're not up to date, grab the latest version and let's get started! +## How it works + +TGI leverages the [outlines](https://github.com/outlines-dev/outlines) library to efficiently parse and compile the grammatical structures and tools specified by users. This integration transforms the defined grammars into an intermediate representation that acts as a framework to guide and constrain content generation, ensuring that outputs adhere to the specified grammatical rules. + ## Table of Contents 📚 ### Grammar and Constraints @@ -270,58 +274,58 @@ curl localhost:3000/v1/chat/completions \
Tools used in example below - ```python - tools = [ - { - "type": "function", - "function": { - "name": "get_current_weather", - "description": "Get the current weather", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and state, e.g. San Francisco, CA", - }, - "format": { - "type": "string", - "enum": ["celsius", "fahrenheit"], - "description": "The temperature unit to use. Infer this from the users location.", - }, - }, - "required": ["location", "format"], - }, - }, - }, - { - "type": "function", - "function": { - "name": "get_n_day_weather_forecast", - "description": "Get an N-day weather forecast", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and state, e.g. San Francisco, CA", - }, - "format": { - "type": "string", - "enum": ["celsius", "fahrenheit"], - "description": "The temperature unit to use. Infer this from the users location.", - }, - "num_days": { - "type": "integer", - "description": "The number of days to forecast", - }, - }, - "required": ["location", "format", "num_days"], - }, - }, - } - ] - ``` +```python + tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "format": { + "type": "string", + "enum": ["celsius", "fahrenheit"], + "description": "The temperature unit to use. Infer this from the users location.", + }, + }, + "required": ["location", "format"], + }, + }, + }, + { + "type": "function", + "function": { + "name": "get_n_day_weather_forecast", + "description": "Get an N-day weather forecast", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "format": { + "type": "string", + "enum": ["celsius", "fahrenheit"], + "description": "The temperature unit to use. Infer this from the users location.", + }, + "num_days": { + "type": "integer", + "description": "The number of days to forecast", + }, + }, + "required": ["location", "format", "num_days"], + }, + }, + } + ] +```
From 9192de57cc6802508db41c489a9e0ee9df569de5 Mon Sep 17 00:00:00 2001 From: Martin Iglesias Goyanes Date: Tue, 30 Apr 2024 12:13:23 +0200 Subject: [PATCH 15/22] Fixing frequency penalty (#1811) Thank you so much for the work you are doing, this is my little contribution to this great thing you have built. I hope it is useful and helpful, please don't hesitate to discuss any matters that are not clear! I am basing my implementation of frequency penalty on OpenAI's implementation: https://platform.openai.com/docs/guides/text-generation/parameter-details The problem I see with TGI's current implementation is that is not taking into account the frequency of tokens which have already been sampled in the current generation stream. Also, the scaling is of the adjusted token logits is done differently for positive and negative logits. While in OpenAI's implementation token frequency is taking into account and the scaling is always done with a subtraction (if penalty is positive) or add operation (if penalty is negative). This leads to corrupt generations as I mentioned in issue #1810 . Moreover, after my tests, other issues are also gone like the one about some request's with ``penalty_frequency = 1.0`` overruling other requests (with ``frequency_penalty = 0.0``) in the same batch and therefore corrupting all generations in the batch. Basically, padding does not affect this implementation so I believe this ``score *= input_ids.ne(0)`` is not needed anymore. Frequency penalty | -1.0 | 0.0 | 1.0 -- | -- | -- | -- Before my change | https://paste.mozilla.org/JxqGJkWY | https://paste.mozilla.org/hrztJ56h | https://paste.mozilla.org/pBSEH2zw After my change | https://paste.mozilla.org/7gXCi7zo | https://paste.mozilla.org/ZR9rJ92g | https://paste.mozilla.org/gHaD2YnC --------- Co-authored-by: martini --- .gitignore | 2 ++ .../utils/logits_process.py | 23 +++++++++++-------- 2 files changed, 16 insertions(+), 9 deletions(-) diff --git a/.gitignore b/.gitignore index b3ca772b..2ac2f6b4 100644 --- a/.gitignore +++ b/.gitignore @@ -11,3 +11,5 @@ server/exllama_kernels/exllama_kernels/hip_func/ *_hip.cuh server/exllama_kernels/exllama_kernels/hip_buffers.cuh server/exllama_kernels/exllama_kernels/exllama_ext_hip.cpp + +data/ diff --git a/server/text_generation_server/utils/logits_process.py b/server/text_generation_server/utils/logits_process.py index 2decee53..6b915437 100644 --- a/server/text_generation_server/utils/logits_process.py +++ b/server/text_generation_server/utils/logits_process.py @@ -151,7 +151,8 @@ class FrequencyPenaltyLogitsProcessor(LogitsProcessor): class HeterogeneousFrequencyPenaltyLogitsProcessor(LogitsProcessor): r""" - Frequency penalty as defined by OpenAI + Frequency penalty as defined by OpenAI in + https://platform.openai.com/docs/guides/text-generation/parameter-details Args: frequency_penalty (`List[float]`): @@ -165,15 +166,19 @@ class HeterogeneousFrequencyPenaltyLogitsProcessor(LogitsProcessor): ).unsqueeze(1) def __call__(self, input_ids: torch.Tensor, scores: torch.Tensor) -> torch.Tensor: - score = torch.gather(scores, 1, input_ids) - # if score < 0 then penalty has to be multiplied to reduce the previous token probability - score = -torch.where( - score < 0, score * self.penalty_tensor, score / self.penalty_tensor - ) - # set score to 0 where input_ids is a padding token - score *= input_ids.ne(0) + batch_size, input_size = input_ids.size() + vocab_size = scores.size(1) - return scores.scatter_add_(1, input_ids, score) + # Calculate the frequency for each token so far + token_freq = torch.zeros(batch_size, vocab_size, device=input_ids.device) + token_freq.scatter_add_( + 1, input_ids, torch.ones_like(input_ids, dtype=torch.float) + ) + token_freq /= input_size + + # Apply the frequency penalty to logits + scores -= token_freq * self.penalty_tensor + return scores def filter(self, indices): self.penalty = [self.penalty[i] for i in indices] From b2c982750a398a562fe7e442d289d629e62b4303 Mon Sep 17 00:00:00 2001 From: drbh Date: Tue, 30 Apr 2024 06:14:39 -0400 Subject: [PATCH 16/22] feat: add vlm docs and simple examples (#1812) This PR start to add documentation for visual language models --- docs/source/_toctree.yml | 3 + .../basic_tutorials/visual_language_models.md | 170 ++++++++++++++++++ 2 files changed, 173 insertions(+) create mode 100644 docs/source/basic_tutorials/visual_language_models.md diff --git a/docs/source/_toctree.yml b/docs/source/_toctree.yml index 1598c248..79a2102f 100644 --- a/docs/source/_toctree.yml +++ b/docs/source/_toctree.yml @@ -25,6 +25,8 @@ title: Non-core Model Serving - local: basic_tutorials/safety title: Safety + - local: basic_tutorials/visual_language_models + title: Visual Language Models title: Tutorials - sections: - local: conceptual/streaming @@ -43,4 +45,5 @@ title: Speculation (Medusa, ngram) - local: conceptual/guidance title: Guidance, JSON, tools (using outlines) + title: Conceptual Guides diff --git a/docs/source/basic_tutorials/visual_language_models.md b/docs/source/basic_tutorials/visual_language_models.md new file mode 100644 index 00000000..e804ef09 --- /dev/null +++ b/docs/source/basic_tutorials/visual_language_models.md @@ -0,0 +1,170 @@ +# Vision Language Model Inference in TGI + +Visual Language Model (VLM) are models that consume both image and text inputs to generate text. + +VLM's are trained on a combination of image and text data and can handle a wide range of tasks, such as image captioning, visual question answering, and visual dialog. + +> What distinguishes VLMs from other text and image models is their ability to handle long context and generate text that is coherent and relevant to the image even after multiple turns or in some cases, multiple images. + +Below are couple of common use cases for vision language models: + +- **Image Captioning**: Given an image, generate a caption that describes the image. +- **Visual Question Answering (VQA)**: Given an image and a question about the image, generate an answer to the question. +- **Mulimodal Dialog**: Generate response to multiple turns of images and conversations. +- **Image Information Retrieval**: Given an image, retrieve information from the image. + +## How to Use a Vision Language Model? + +### Hugging Face Hub Python Library + +To infer with vision language models through Python, you can use the [`huggingface_hub`](https://pypi.org/project/huggingface-hub/) library. The `InferenceClient` class provides a simple way to interact with the [Inference API](https://huggingface.co/docs/api-inference/index). Images can be passed as URLs or base64-encoded strings. The `InferenceClient` will automatically detect the image format. + +```python +from huggingface_hub import InferenceClient + +client = InferenceClient("http://127.0.0.1:3000") +image = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/rabbit.png" +prompt = f"![]({image})What is this a picture of?\n\n" +for token in client.text_generation(prompt, max_new_tokens=16, stream=True): + print(token) + +# This is a picture of an anthropomorphic rabbit in a space suit. +``` + +```python +from huggingface_hub import InferenceClient +import base64 +import requests +import io + +client = InferenceClient("http://127.0.0.1:3000") + +# read image from local file +image_path = "rabbit.png" +with open(image_path, "rb") as f: + image = base64.b64encode(f.read()).decode("utf-8") + +image = f"data:image/png;base64,{image}" +prompt = f"![]({image})What is this a picture of?\n\n" + +for token in client.text_generation(prompt, max_new_tokens=10, stream=True): + print(token) + +# This is a picture of an anthropomorphic rabbit in a space suit. +``` + +If you want additional details, you can add `details=True`. In this case, you get a `TextGenerationStreamResponse` which contains additional information such as the probabilities and the tokens. For the final response in the stream, it also returns the full generated text. + +### Inference Through Sending `cURL` Requests + +To use the `generate_stream` endpoint with curl, you can add the `-N` flag. This flag disables curl default buffering and shows data as it arrives from the server. + +```bash +curl -N 127.0.0.1:3000/generate_stream \ + -X POST \ + -d '{"inputs":"![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/rabbit.png)What is this a picture of?\n\n","parameters":{"max_new_tokens":16, "seed": 42}}' \ + -H 'Content-Type: application/json' + +# ... +# data:{"index":16,"token":{"id":28723,"text":".","logprob":-0.6196289,"special":false},"generated_text":"This is a picture of an anthropomorphic rabbit in a space suit.","details":null} +``` + +### Inference Through JavaScript + +First, we need to install the `@huggingface/inference` library. + +```bash +npm install @huggingface/inference +``` + +If you're using the free Inference API, you can use [Huggingface.js](https://huggingface.co/docs/huggingface.js/inference/README)'s `HfInference`. If you're using inference endpoints, you can use `HfInferenceEndpoint` class to easily interact with the Inference API. + +We can create a `HfInferenceEndpoint` providing our endpoint URL and We can create a `HfInferenceEndpoint` providing our endpoint URL and [Hugging Face access token](https://huggingface.co/settings/tokens). + +```js +import { HfInferenceEndpoint } from "@huggingface/inference"; + +const hf = new HfInferenceEndpoint("http://127.0.0.1:3000", "HF_TOKEN"); + +const prompt = + "![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/rabbit.png)What is this a picture of?\n\n"; + +const stream = hf.textGenerationStream({ + inputs: prompt, + parameters: { max_new_tokens: 16, seed: 42 }, +}); +for await (const r of stream) { + // yield the generated token + process.stdout.write(r.token.text); +} + +// This is a picture of an anthropomorphic rabbit in a space suit. +``` + +## Combining Vision Language Models with Other Features + +VLMs in TGI have several advantages, for example these models can be used in tandem with other features for more complex tasks. For example, you can use VLMs with [Guided Generation](/docs/conceptual/guided-generation) to generate specific JSON data from an image. + +
+ +
+ +For example we can extract information from the rabbit image and generate a JSON object with the location, activity, number of animals seen, and the animals seen. That would look like this: + +```json +{ + "activity": "Standing", + "animals": ["Rabbit"], + "animals_seen": 1, + "location": "Rocky surface with mountains in the background and a red light on the rabbit's chest" +} +``` + +All we need to do is provide a JSON schema to the VLM model and it will generate the JSON object for us. + +```bash +curl localhost:3000/generate \ + -X POST \ + -H 'Content-Type: application/json' \ + -d '{ + "inputs":"![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/rabbit.png)What is this a picture of?\n\n", + "parameters": { + "max_new_tokens": 100, + "seed": 42, + "grammar": { + "type": "json", + "value": { + "properties": { + "location": { + "type": "string" + }, + "activity": { + "type": "string" + }, + "animals_seen": { + "type": "integer", + "minimum": 1, + "maximum": 5 + }, + "animals": { + "type": "array", + "items": { + "type": "string" + } + } + }, + "required": ["location", "activity", "animals_seen", "animals"] + } + } + } +}' + +# { +# "generated_text": "{ \"activity\": \"Standing\", \"animals\": [ \"Rabbit\" ], \"animals_seen\": 1, \"location\": \"Rocky surface with mountains in the background and a red light on the rabbit's chest\" }" +# } +``` + +Want to learn more about how Vision Language Models work? Check out the [awesome blog post on the topic](https://huggingface.co/blog/vlms). From c99ecd77ecc079a67c176b46b61c7a2d85ac068f Mon Sep 17 00:00:00 2001 From: drbh Date: Tue, 30 Apr 2024 06:18:32 -0400 Subject: [PATCH 17/22] Handle images in chat api (#1828) This PR allows for messages to be formatted as simple strings, or as an array of objects including image urls. This is done by formatting content arrays into a simple string. Example using `llava-hf/llava-v1.6-mistral-7b-hf` ```bash curl localhost: 3000/v1/chat/completions \ -X POST \ -H 'Content-Type: application/json' \ -d '{ "model": "tgi", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Whats in this image?" }, { "type": "image_url", "image_url": { "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/rabbit.png" } } ] } ], "stream": false, "max_tokens": 20, "seed": 42 }' ``` is equivlant to this more simple request ```bash curl localhost: 3000/v1/chat/completions \ -X POST \ -H 'Content-Type: application/json' \ -d '{ "model": "tgi", "messages": [ { "role": "user", "content": "Whats in this image?\n![](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/rabbit.png)" } ], "stream": false, "max_tokens": 20, "seed": 42 }' ``` output ``` # {"id":"","object":"text_completion","created":1714406985,"model":"llava-hf/llava-v1.6-mistral-7b-hf","system_fingerprint":"2.0.1-native","choices":[{"index":0,"message":{"role":"assistant","content":" This is an illustration of an anthropomorphic rabbit in a spacesuit, standing on what"},"logprobs":null,"finish_reason":"length"}],"usage":{"prompt_tokens":2945,"completion_tokens":20,"total_tokens":2965}}% ``` --------- Co-authored-by: Nicolas Patry --- router/src/lib.rs | 65 ++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 64 insertions(+), 1 deletion(-) diff --git a/router/src/lib.rs b/router/src/lib.rs index 9b9097f6..fac4c14e 100644 --- a/router/src/lib.rs +++ b/router/src/lib.rs @@ -884,12 +884,75 @@ pub(crate) struct ToolCall { pub function: FunctionDefinition, } -#[derive(Clone, Deserialize, ToSchema, Serialize)] +#[derive(Clone, Deserialize, Serialize, ToSchema, Default, Debug)] +pub(crate) struct Text { + #[serde(default)] + pub text: String, +} + +#[derive(Clone, Deserialize, Serialize, ToSchema, Default, Debug)] +pub(crate) struct ImageUrl { + #[serde(default)] + pub url: String, +} + +#[derive(Clone, Deserialize, Serialize, ToSchema, Default, Debug)] +pub(crate) struct Content { + pub r#type: String, + #[serde(default, skip_serializing_if = "Option::is_none")] + pub text: Option, + #[serde(default, skip_serializing_if = "Option::is_none")] + pub image_url: Option, +} + +mod message_content_serde { + use super::*; + use serde::de; + use serde::Deserializer; + use serde_json::Value; + + pub fn deserialize<'de, D>(deserializer: D) -> Result, D::Error> + where + D: Deserializer<'de>, + { + let value = Value::deserialize(deserializer)?; + match value { + Value::String(s) => Ok(Some(s)), + Value::Array(arr) => { + let results: Result, _> = arr + .into_iter() + .map(|v| { + let content: Content = + serde_json::from_value(v).map_err(de::Error::custom)?; + match content.r#type.as_str() { + "text" => Ok(content.text.unwrap_or_default()), + "image_url" => { + if let Some(url) = content.image_url { + Ok(format!("![]({})", url.url)) + } else { + Ok(String::new()) + } + } + _ => Err(de::Error::custom("invalid content type")), + } + }) + .collect(); + + results.map(|strings| Some(strings.join(""))) + } + Value::Null => Ok(None), + _ => Err(de::Error::custom("invalid token format")), + } + } +} + +#[derive(Clone, Deserialize, ToSchema, Serialize, Debug)] pub(crate) struct Message { #[schema(example = "user")] pub role: String, #[serde(skip_serializing_if = "Option::is_none")] #[schema(example = "My name is David and I")] + #[serde(deserialize_with = "message_content_serde::deserialize")] pub content: Option, #[serde(default, skip_serializing_if = "Option::is_none")] #[schema(example = "\"David\"")] From b4ef038837c9264fa7665d5a6baf130f8dbb145b Mon Sep 17 00:00:00 2001 From: OlivierDehaene Date: Tue, 30 Apr 2024 14:04:28 +0200 Subject: [PATCH 18/22] chore: update torch (#1730) Co-authored-by: Nicolas Patry --- Dockerfile | 7 +++++-- server/Makefile-vllm | 2 +- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/Dockerfile b/Dockerfile index c2ae4c85..333f7c91 100644 --- a/Dockerfile +++ b/Dockerfile @@ -39,7 +39,7 @@ RUN cargo build --release # Adapted from: https://github.com/pytorch/pytorch/blob/master/Dockerfile FROM nvidia/cuda:12.1.0-devel-ubuntu22.04 as pytorch-install -ARG PYTORCH_VERSION=2.1.1 +ARG PYTORCH_VERSION=2.3.0 ARG PYTHON_VERSION=3.10 # Keep in sync with `server/pyproject.toml ARG CUDA_VERSION=12.1 @@ -149,6 +149,8 @@ FROM kernel-builder as vllm-builder WORKDIR /usr/src +ENV TORCH_CUDA_ARCH_LIST="7.0 7.5 8.0 8.6 8.9 9.0+PTX" + COPY server/Makefile-vllm Makefile # Build specific version of vllm @@ -210,7 +212,7 @@ COPY --from=vllm-builder /usr/src/vllm/build/lib.linux-x86_64-cpython-310 /opt/c COPY --from=mamba-builder /usr/src/mamba/build/lib.linux-x86_64-cpython-310/ /opt/conda/lib/python3.10/site-packages COPY --from=mamba-builder /usr/src/causal-conv1d/build/lib.linux-x86_64-cpython-310/ /opt/conda/lib/python3.10/site-packages -# Install vllm/flash-attention dependencies +# Install flash-attention dependencies RUN pip install einops --no-cache-dir # Install server @@ -246,6 +248,7 @@ ENTRYPOINT ["./entrypoint.sh"] FROM base COPY ./tgi-entrypoint.sh /tgi-entrypoint.sh +RUN chmod +x /tgi-entrypoint.sh ENTRYPOINT ["/tgi-entrypoint.sh"] CMD ["--json-output"] diff --git a/server/Makefile-vllm b/server/Makefile-vllm index ada484a6..9999ad89 100644 --- a/server/Makefile-vllm +++ b/server/Makefile-vllm @@ -4,7 +4,7 @@ vllm-cuda: git clone https://github.com/OlivierDehaene/vllm.git vllm build-vllm-cuda: vllm-cuda - cd vllm && git fetch && git checkout 4bec8cee87f6bb8cebaec297029713cd2082e0b2 + cd vllm && git fetch && git checkout 3d4693536dcb69f036c26b016a35839b99ebed59 cd vllm && python setup.py build install-vllm-cuda: build-vllm-cuda From dccab72549635c7eb5ddb17f43f0b7cdff07c214 Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Tue, 30 Apr 2024 18:15:35 +0200 Subject: [PATCH 19/22] (chore): torch 2.3.0 (#1833) # What does this PR do? Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. --- server/Makefile-vllm | 4 +- server/poetry.lock | 922 ++++++++++++++++++----------------- server/pyproject.toml | 6 +- server/requirements_cuda.txt | 16 +- server/requirements_rocm.txt | 16 +- 5 files changed, 507 insertions(+), 457 deletions(-) diff --git a/server/Makefile-vllm b/server/Makefile-vllm index 9999ad89..6f36c679 100644 --- a/server/Makefile-vllm +++ b/server/Makefile-vllm @@ -1,10 +1,10 @@ vllm-cuda: # Clone vllm pip install -U ninja packaging --no-cache-dir - git clone https://github.com/OlivierDehaene/vllm.git vllm + git clone https://github.com/Narsil/vllm.git vllm build-vllm-cuda: vllm-cuda - cd vllm && git fetch && git checkout 3d4693536dcb69f036c26b016a35839b99ebed59 + cd vllm && git fetch && git checkout b5dfc61db88a81069e45b44f7cc99bd9e62a60fa cd vllm && python setup.py build install-vllm-cuda: build-vllm-cuda diff --git a/server/poetry.lock b/server/poetry.lock index aea9c4c2..3a554af0 100644 --- a/server/poetry.lock +++ b/server/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 1.6.1 and should not be changed by hand. +# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand. [[package]] name = "accelerate" @@ -359,45 +359,43 @@ files = [ [[package]] name = "datasets" -version = "2.18.0" +version = "2.14.4" description = "HuggingFace community-driven open-source library of datasets" optional = true python-versions = ">=3.8.0" files = [ - {file = "datasets-2.18.0-py3-none-any.whl", hash = "sha256:f1bbf0e2896917a914de01cbd37075b14deea3837af87ad0d9f697388ccaeb50"}, - {file = "datasets-2.18.0.tar.gz", hash = "sha256:cdf8b8c6abf7316377ba4f49f9589a4c74556d6b481afd0abd2284f3d69185cb"}, + {file = "datasets-2.14.4-py3-none-any.whl", hash = "sha256:29336bd316a7d827ccd4da2236596279b20ca2ac78f64c04c9483da7cbc2459b"}, + {file = "datasets-2.14.4.tar.gz", hash = "sha256:ef29c2b5841de488cd343cfc26ab979bff77efa4d2285af51f1ad7db5c46a83b"}, ] [package.dependencies] aiohttp = "*" -dill = ">=0.3.0,<0.3.9" -filelock = "*" -fsspec = {version = ">=2023.1.0,<=2024.2.0", extras = ["http"]} -huggingface-hub = ">=0.19.4" +dill = ">=0.3.0,<0.3.8" +fsspec = {version = ">=2021.11.1", extras = ["http"]} +huggingface-hub = ">=0.14.0,<1.0.0" multiprocess = "*" numpy = ">=1.17" packaging = "*" pandas = "*" -pyarrow = ">=12.0.0" -pyarrow-hotfix = "*" +pyarrow = ">=8.0.0" pyyaml = ">=5.1" requests = ">=2.19.0" tqdm = ">=4.62.1" xxhash = "*" [package.extras] -apache-beam = ["apache-beam (>=2.26.0)"] +apache-beam = ["apache-beam (>=2.26.0,<2.44.0)"] audio = ["librosa", "soundfile (>=0.12.1)"] benchmarks = ["tensorflow (==2.12.0)", "torch (==2.0.1)", "transformers (==4.30.1)"] -dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "ruff (>=0.3.0)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.2.0,!=2.6.0,!=2.6.1)", "tensorflow (>=2.3,!=2.6.0,!=2.6.1)", "tensorflow-macos", "tiktoken", "torch", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"] +dev = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0,<2.44.0)", "black (>=23.1,<24.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "pyyaml (>=5.3.1)", "rarfile (>=4.0)", "ruff (>=0.0.241)", "s3fs", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy (<2.0.0)", "tensorflow (>=2.2.0,!=2.6.0,!=2.6.1)", "tensorflow (>=2.3,!=2.6.0,!=2.6.1)", "tensorflow-macos", "tiktoken", "torch", "transformers", "zstandard"] docs = ["s3fs", "tensorflow (>=2.2.0,!=2.6.0,!=2.6.1)", "tensorflow-macos", "torch", "transformers"] -jax = ["jax (>=0.3.14)", "jaxlib (>=0.3.14)"] +jax = ["jax (>=0.2.8,!=0.3.2,<=0.3.25)", "jaxlib (>=0.1.65,<=0.3.25)"] metrics-tests = ["Werkzeug (>=1.0.1)", "accelerate", "bert-score (>=0.3.6)", "jiwer", "langdetect", "mauve-text", "nltk", "requests-file (>=1.5.1)", "rouge-score", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "spacy (>=3.0.0)", "texttable (>=1.6.3)", "tldextract", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "typer (<0.5.0)"] -quality = ["ruff (>=0.3.0)"] +quality = ["black (>=23.1,<24.0)", "pyyaml (>=5.3.1)", "ruff (>=0.0.241)"] s3 = ["s3fs"] tensorflow = ["tensorflow (>=2.2.0,!=2.6.0,!=2.6.1)", "tensorflow-macos"] tensorflow-gpu = ["tensorflow-gpu (>=2.2.0,!=2.6.0,!=2.6.1)"] -tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "jax (>=0.3.14)", "jaxlib (>=0.3.14)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy", "tensorflow (>=2.3,!=2.6.0,!=2.6.1)", "tensorflow-macos", "tiktoken", "torch (>=2.0.0)", "transformers", "typing-extensions (>=4.6.1)", "zstandard"] +tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0,<2.44.0)", "elasticsearch (<8.0.0)", "faiss-cpu (>=1.6.4)", "joblib (<1.3.0)", "joblibspark", "librosa", "lz4", "py7zr", "pyspark (>=3.4)", "pytest", "pytest-datadir", "pytest-xdist", "rarfile (>=4.0)", "s3fs (>=2021.11.1)", "soundfile (>=0.12.1)", "sqlalchemy (<2.0.0)", "tensorflow (>=2.3,!=2.6.0,!=2.6.1)", "tensorflow-macos", "tiktoken", "torch", "transformers", "zstandard"] torch = ["torch"] vision = ["Pillow (>=6.2.1)"] @@ -420,18 +418,17 @@ dev = ["PyTest", "PyTest-Cov", "bump2version (<1)", "sphinx (<2)", "tox"] [[package]] name = "dill" -version = "0.3.8" +version = "0.3.7" description = "serialize all of Python" optional = true -python-versions = ">=3.8" +python-versions = ">=3.7" files = [ - {file = "dill-0.3.8-py3-none-any.whl", hash = "sha256:c36ca9ffb54365bdd2f8eb3eff7d2a21237f8452b57ace88b1ac615b7e815bd7"}, - {file = "dill-0.3.8.tar.gz", hash = "sha256:3ebe3c479ad625c4553aca177444d89b486b1d84982eeacded644afc0cf797ca"}, + {file = "dill-0.3.7-py3-none-any.whl", hash = "sha256:76b122c08ef4ce2eedcd4d1abd8e641114bfc6c2867f49f3c41facf65bf19f5e"}, + {file = "dill-0.3.7.tar.gz", hash = "sha256:cc1c8b182eb3013e24bd475ff2e9295af86c1a38eb1aff128dac8962a9ce3c03"}, ] [package.extras] graph = ["objgraph (>=1.7.2)"] -profile = ["gprof2dot (>=2022.7.29)"] [[package]] name = "diskcache" @@ -457,13 +454,13 @@ files = [ [[package]] name = "exceptiongroup" -version = "1.2.0" +version = "1.2.1" description = "Backport of PEP 654 (exception groups)" optional = false python-versions = ">=3.7" files = [ - {file = "exceptiongroup-1.2.0-py3-none-any.whl", hash = "sha256:4bfd3996ac73b41e9b9628b04e079f193850720ea5945fc96a08633c66912f14"}, - {file = "exceptiongroup-1.2.0.tar.gz", hash = "sha256:91f5c769735f051a4290d52edd0858999b57e5876e9f85937691bd4c9fa3ed68"}, + {file = "exceptiongroup-1.2.1-py3-none-any.whl", hash = "sha256:5258b9ed329c5bbdd31a309f53cbfb0b155341807f6ff7606a1e801a891b29ad"}, + {file = "exceptiongroup-1.2.1.tar.gz", hash = "sha256:a4785e48b045528f5bfe627b6ad554ff32def154f42372786903b7abcfe1aa16"}, ] [package.extras] @@ -471,13 +468,13 @@ test = ["pytest (>=6)"] [[package]] name = "filelock" -version = "3.13.4" +version = "3.14.0" description = "A platform independent file lock." optional = false python-versions = ">=3.8" files = [ - {file = "filelock-3.13.4-py3-none-any.whl", hash = "sha256:404e5e9253aa60ad457cae1be07c0f0ca90a63931200a47d9b6a6af84fd7b45f"}, - {file = "filelock-3.13.4.tar.gz", hash = "sha256:d13f466618bfde72bd2c18255e269f72542c6e70e7bac83a0232d6b1cc5c8cf4"}, + {file = "filelock-3.14.0-py3-none-any.whl", hash = "sha256:43339835842f110ca7ae60f1e1c160714c5a6afd15a2873419ab185334975c0f"}, + {file = "filelock-3.14.0.tar.gz", hash = "sha256:6ea72da3be9b8c82afd3edcf99f2fffbb5076335a5ae4d03248bb5b6c3eae78a"}, ] [package.extras] @@ -573,13 +570,13 @@ files = [ [[package]] name = "fsspec" -version = "2024.2.0" +version = "2024.3.1" description = "File-system specification" optional = false python-versions = ">=3.8" files = [ - {file = "fsspec-2024.2.0-py3-none-any.whl", hash = "sha256:817f969556fa5916bc682e02ca2045f96ff7f586d45110fcb76022063ad2c7d8"}, - {file = "fsspec-2024.2.0.tar.gz", hash = "sha256:b6ad1a679f760dda52b1168c859d01b7b80648ea6f7f7c7f5a8a91dc3f3ecb84"}, + {file = "fsspec-2024.3.1-py3-none-any.whl", hash = "sha256:918d18d41bf73f0e2b261824baeb1b124bcf771767e3a26425cd7dec3332f512"}, + {file = "fsspec-2024.3.1.tar.gz", hash = "sha256:f39780e282d7d117ffb42bb96992f8a90795e4d0fb0f661a70ca39fe9c43ded9"}, ] [package.dependencies] @@ -645,166 +642,166 @@ testing = ["protobuf (>=4.21.9)"] [[package]] name = "grpcio" -version = "1.62.1" +version = "1.62.2" description = "HTTP/2-based RPC framework" optional = false python-versions = ">=3.7" files = [ - {file = "grpcio-1.62.1-cp310-cp310-linux_armv7l.whl", hash = "sha256:179bee6f5ed7b5f618844f760b6acf7e910988de77a4f75b95bbfaa8106f3c1e"}, - {file = "grpcio-1.62.1-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:48611e4fa010e823ba2de8fd3f77c1322dd60cb0d180dc6630a7e157b205f7ea"}, - {file = "grpcio-1.62.1-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:b2a0e71b0a2158aa4bce48be9f8f9eb45cbd17c78c7443616d00abbe2a509f6d"}, - {file = "grpcio-1.62.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:fbe80577c7880911d3ad65e5ecc997416c98f354efeba2f8d0f9112a67ed65a5"}, - {file = "grpcio-1.62.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:58f6c693d446964e3292425e1d16e21a97a48ba9172f2d0df9d7b640acb99243"}, - {file = "grpcio-1.62.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:77c339403db5a20ef4fed02e4d1a9a3d9866bf9c0afc77a42234677313ea22f3"}, - {file = "grpcio-1.62.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b5a4ea906db7dec694098435d84bf2854fe158eb3cd51e1107e571246d4d1d70"}, - {file = "grpcio-1.62.1-cp310-cp310-win32.whl", hash = "sha256:4187201a53f8561c015bc745b81a1b2d278967b8de35f3399b84b0695e281d5f"}, - {file = "grpcio-1.62.1-cp310-cp310-win_amd64.whl", hash = "sha256:844d1f3fb11bd1ed362d3fdc495d0770cfab75761836193af166fee113421d66"}, - {file = "grpcio-1.62.1-cp311-cp311-linux_armv7l.whl", hash = "sha256:833379943d1728a005e44103f17ecd73d058d37d95783eb8f0b28ddc1f54d7b2"}, - {file = "grpcio-1.62.1-cp311-cp311-macosx_10_10_universal2.whl", hash = "sha256:c7fcc6a32e7b7b58f5a7d27530669337a5d587d4066060bcb9dee7a8c833dfb7"}, - {file = "grpcio-1.62.1-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:fa7d28eb4d50b7cbe75bb8b45ed0da9a1dc5b219a0af59449676a29c2eed9698"}, - {file = "grpcio-1.62.1-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:48f7135c3de2f298b833be8b4ae20cafe37091634e91f61f5a7eb3d61ec6f660"}, - {file = "grpcio-1.62.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:71f11fd63365ade276c9d4a7b7df5c136f9030e3457107e1791b3737a9b9ed6a"}, - {file = "grpcio-1.62.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:4b49fd8fe9f9ac23b78437da94c54aa7e9996fbb220bac024a67469ce5d0825f"}, - {file = "grpcio-1.62.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:482ae2ae78679ba9ed5752099b32e5fe580443b4f798e1b71df412abf43375db"}, - {file = "grpcio-1.62.1-cp311-cp311-win32.whl", hash = "sha256:1faa02530b6c7426404372515fe5ddf66e199c2ee613f88f025c6f3bd816450c"}, - {file = "grpcio-1.62.1-cp311-cp311-win_amd64.whl", hash = "sha256:5bd90b8c395f39bc82a5fb32a0173e220e3f401ff697840f4003e15b96d1befc"}, - {file = "grpcio-1.62.1-cp312-cp312-linux_armv7l.whl", hash = "sha256:b134d5d71b4e0837fff574c00e49176051a1c532d26c052a1e43231f252d813b"}, - {file = "grpcio-1.62.1-cp312-cp312-macosx_10_10_universal2.whl", hash = "sha256:d1f6c96573dc09d50dbcbd91dbf71d5cf97640c9427c32584010fbbd4c0e0037"}, - {file = "grpcio-1.62.1-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:359f821d4578f80f41909b9ee9b76fb249a21035a061a327f91c953493782c31"}, - {file = "grpcio-1.62.1-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a485f0c2010c696be269184bdb5ae72781344cb4e60db976c59d84dd6354fac9"}, - {file = "grpcio-1.62.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b50b09b4dc01767163d67e1532f948264167cd27f49e9377e3556c3cba1268e1"}, - {file = "grpcio-1.62.1-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:3227c667dccbe38f2c4d943238b887bac588d97c104815aecc62d2fd976e014b"}, - {file = "grpcio-1.62.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:3952b581eb121324853ce2b191dae08badb75cd493cb4e0243368aa9e61cfd41"}, - {file = "grpcio-1.62.1-cp312-cp312-win32.whl", hash = "sha256:83a17b303425104d6329c10eb34bba186ffa67161e63fa6cdae7776ff76df73f"}, - {file = "grpcio-1.62.1-cp312-cp312-win_amd64.whl", hash = "sha256:6696ffe440333a19d8d128e88d440f91fb92c75a80ce4b44d55800e656a3ef1d"}, - {file = "grpcio-1.62.1-cp37-cp37m-linux_armv7l.whl", hash = "sha256:e3393b0823f938253370ebef033c9fd23d27f3eae8eb9a8f6264900c7ea3fb5a"}, - {file = "grpcio-1.62.1-cp37-cp37m-macosx_10_10_universal2.whl", hash = "sha256:83e7ccb85a74beaeae2634f10eb858a0ed1a63081172649ff4261f929bacfd22"}, - {file = "grpcio-1.62.1-cp37-cp37m-manylinux_2_17_aarch64.whl", hash = "sha256:882020c87999d54667a284c7ddf065b359bd00251fcd70279ac486776dbf84ec"}, - {file = "grpcio-1.62.1-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a10383035e864f386fe096fed5c47d27a2bf7173c56a6e26cffaaa5a361addb1"}, - {file = "grpcio-1.62.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:960edebedc6b9ada1ef58e1c71156f28689978188cd8cff3b646b57288a927d9"}, - {file = "grpcio-1.62.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:23e2e04b83f347d0aadde0c9b616f4726c3d76db04b438fd3904b289a725267f"}, - {file = "grpcio-1.62.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:978121758711916d34fe57c1f75b79cdfc73952f1481bb9583399331682d36f7"}, - {file = "grpcio-1.62.1-cp37-cp37m-win_amd64.whl", hash = "sha256:9084086190cc6d628f282e5615f987288b95457292e969b9205e45b442276407"}, - {file = "grpcio-1.62.1-cp38-cp38-linux_armv7l.whl", hash = "sha256:22bccdd7b23c420a27fd28540fb5dcbc97dc6be105f7698cb0e7d7a420d0e362"}, - {file = "grpcio-1.62.1-cp38-cp38-macosx_10_10_universal2.whl", hash = "sha256:8999bf1b57172dbc7c3e4bb3c732658e918f5c333b2942243f10d0d653953ba9"}, - {file = "grpcio-1.62.1-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:d9e52558b8b8c2f4ac05ac86344a7417ccdd2b460a59616de49eb6933b07a0bd"}, - {file = "grpcio-1.62.1-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1714e7bc935780bc3de1b3fcbc7674209adf5208ff825799d579ffd6cd0bd505"}, - {file = "grpcio-1.62.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c8842ccbd8c0e253c1f189088228f9b433f7a93b7196b9e5b6f87dba393f5d5d"}, - {file = "grpcio-1.62.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:1f1e7b36bdff50103af95a80923bf1853f6823dd62f2d2a2524b66ed74103e49"}, - {file = "grpcio-1.62.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:bba97b8e8883a8038606480d6b6772289f4c907f6ba780fa1f7b7da7dfd76f06"}, - {file = "grpcio-1.62.1-cp38-cp38-win32.whl", hash = "sha256:a7f615270fe534548112a74e790cd9d4f5509d744dd718cd442bf016626c22e4"}, - {file = "grpcio-1.62.1-cp38-cp38-win_amd64.whl", hash = "sha256:e6c8c8693df718c5ecbc7babb12c69a4e3677fd11de8886f05ab22d4e6b1c43b"}, - {file = "grpcio-1.62.1-cp39-cp39-linux_armv7l.whl", hash = "sha256:73db2dc1b201d20ab7083e7041946910bb991e7e9761a0394bbc3c2632326483"}, - {file = "grpcio-1.62.1-cp39-cp39-macosx_10_10_universal2.whl", hash = "sha256:407b26b7f7bbd4f4751dbc9767a1f0716f9fe72d3d7e96bb3ccfc4aace07c8de"}, - {file = "grpcio-1.62.1-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:f8de7c8cef9261a2d0a62edf2ccea3d741a523c6b8a6477a340a1f2e417658de"}, - {file = "grpcio-1.62.1-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9bd5c8a1af40ec305d001c60236308a67e25419003e9bb3ebfab5695a8d0b369"}, - {file = "grpcio-1.62.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:be0477cb31da67846a33b1a75c611f88bfbcd427fe17701b6317aefceee1b96f"}, - {file = "grpcio-1.62.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:60dcd824df166ba266ee0cfaf35a31406cd16ef602b49f5d4dfb21f014b0dedd"}, - {file = "grpcio-1.62.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:973c49086cabab773525f6077f95e5a993bfc03ba8fc32e32f2c279497780585"}, - {file = "grpcio-1.62.1-cp39-cp39-win32.whl", hash = "sha256:12859468e8918d3bd243d213cd6fd6ab07208195dc140763c00dfe901ce1e1b4"}, - {file = "grpcio-1.62.1-cp39-cp39-win_amd64.whl", hash = "sha256:b7209117bbeebdfa5d898205cc55153a51285757902dd73c47de498ad4d11332"}, - {file = "grpcio-1.62.1.tar.gz", hash = "sha256:6c455e008fa86d9e9a9d85bb76da4277c0d7d9668a3bfa70dbe86e9f3c759947"}, + {file = "grpcio-1.62.2-cp310-cp310-linux_armv7l.whl", hash = "sha256:66344ea741124c38588a664237ac2fa16dfd226964cca23ddc96bd4accccbde5"}, + {file = "grpcio-1.62.2-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:5dab7ac2c1e7cb6179c6bfad6b63174851102cbe0682294e6b1d6f0981ad7138"}, + {file = "grpcio-1.62.2-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:3ad00f3f0718894749d5a8bb0fa125a7980a2f49523731a9b1fabf2b3522aa43"}, + {file = "grpcio-1.62.2-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2e72ddfee62430ea80133d2cbe788e0d06b12f865765cb24a40009668bd8ea05"}, + {file = "grpcio-1.62.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:53d3a59a10af4c2558a8e563aed9f256259d2992ae0d3037817b2155f0341de1"}, + {file = "grpcio-1.62.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:a1511a303f8074f67af4119275b4f954189e8313541da7b88b1b3a71425cdb10"}, + {file = "grpcio-1.62.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:b94d41b7412ef149743fbc3178e59d95228a7064c5ab4760ae82b562bdffb199"}, + {file = "grpcio-1.62.2-cp310-cp310-win32.whl", hash = "sha256:a75af2fc7cb1fe25785be7bed1ab18cef959a376cdae7c6870184307614caa3f"}, + {file = "grpcio-1.62.2-cp310-cp310-win_amd64.whl", hash = "sha256:80407bc007754f108dc2061e37480238b0dc1952c855e86a4fc283501ee6bb5d"}, + {file = "grpcio-1.62.2-cp311-cp311-linux_armv7l.whl", hash = "sha256:c1624aa686d4b36790ed1c2e2306cc3498778dffaf7b8dd47066cf819028c3ad"}, + {file = "grpcio-1.62.2-cp311-cp311-macosx_10_10_universal2.whl", hash = "sha256:1c1bb80299bdef33309dff03932264636450c8fdb142ea39f47e06a7153d3063"}, + {file = "grpcio-1.62.2-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:db068bbc9b1fa16479a82e1ecf172a93874540cb84be69f0b9cb9b7ac3c82670"}, + {file = "grpcio-1.62.2-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e2cc8a308780edbe2c4913d6a49dbdb5befacdf72d489a368566be44cadaef1a"}, + {file = "grpcio-1.62.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d0695ae31a89f1a8fc8256050329a91a9995b549a88619263a594ca31b76d756"}, + {file = "grpcio-1.62.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:88b4f9ee77191dcdd8810241e89340a12cbe050be3e0d5f2f091c15571cd3930"}, + {file = "grpcio-1.62.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:2a0204532aa2f1afd467024b02b4069246320405bc18abec7babab03e2644e75"}, + {file = "grpcio-1.62.2-cp311-cp311-win32.whl", hash = "sha256:6e784f60e575a0de554ef9251cbc2ceb8790914fe324f11e28450047f264ee6f"}, + {file = "grpcio-1.62.2-cp311-cp311-win_amd64.whl", hash = "sha256:112eaa7865dd9e6d7c0556c8b04ae3c3a2dc35d62ad3373ab7f6a562d8199200"}, + {file = "grpcio-1.62.2-cp312-cp312-linux_armv7l.whl", hash = "sha256:65034473fc09628a02fb85f26e73885cf1ed39ebd9cf270247b38689ff5942c5"}, + {file = "grpcio-1.62.2-cp312-cp312-macosx_10_10_universal2.whl", hash = "sha256:d2c1771d0ee3cf72d69bb5e82c6a82f27fbd504c8c782575eddb7839729fbaad"}, + {file = "grpcio-1.62.2-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:3abe6838196da518863b5d549938ce3159d809218936851b395b09cad9b5d64a"}, + {file = "grpcio-1.62.2-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c5ffeb269f10cedb4f33142b89a061acda9f672fd1357331dbfd043422c94e9e"}, + {file = "grpcio-1.62.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:404d3b4b6b142b99ba1cff0b2177d26b623101ea2ce51c25ef6e53d9d0d87bcc"}, + {file = "grpcio-1.62.2-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:262cda97efdabb20853d3b5a4c546a535347c14b64c017f628ca0cc7fa780cc6"}, + {file = "grpcio-1.62.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:17708db5b11b966373e21519c4c73e5a750555f02fde82276ea2a267077c68ad"}, + {file = "grpcio-1.62.2-cp312-cp312-win32.whl", hash = "sha256:b7ec9e2f8ffc8436f6b642a10019fc513722858f295f7efc28de135d336ac189"}, + {file = "grpcio-1.62.2-cp312-cp312-win_amd64.whl", hash = "sha256:aa787b83a3cd5e482e5c79be030e2b4a122ecc6c5c6c4c42a023a2b581fdf17b"}, + {file = "grpcio-1.62.2-cp37-cp37m-linux_armv7l.whl", hash = "sha256:cfd23ad29bfa13fd4188433b0e250f84ec2c8ba66b14a9877e8bce05b524cf54"}, + {file = "grpcio-1.62.2-cp37-cp37m-macosx_10_10_universal2.whl", hash = "sha256:af15e9efa4d776dfcecd1d083f3ccfb04f876d613e90ef8432432efbeeac689d"}, + {file = "grpcio-1.62.2-cp37-cp37m-manylinux_2_17_aarch64.whl", hash = "sha256:f4aa94361bb5141a45ca9187464ae81a92a2a135ce2800b2203134f7a1a1d479"}, + {file = "grpcio-1.62.2-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:82af3613a219512a28ee5c95578eb38d44dd03bca02fd918aa05603c41018051"}, + {file = "grpcio-1.62.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:55ddaf53474e8caeb29eb03e3202f9d827ad3110475a21245f3c7712022882a9"}, + {file = "grpcio-1.62.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:c79b518c56dddeec79e5500a53d8a4db90da995dfe1738c3ac57fe46348be049"}, + {file = "grpcio-1.62.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:a5eb4844e5e60bf2c446ef38c5b40d7752c6effdee882f716eb57ae87255d20a"}, + {file = "grpcio-1.62.2-cp37-cp37m-win_amd64.whl", hash = "sha256:aaae70364a2d1fb238afd6cc9fcb10442b66e397fd559d3f0968d28cc3ac929c"}, + {file = "grpcio-1.62.2-cp38-cp38-linux_armv7l.whl", hash = "sha256:1bcfe5070e4406f489e39325b76caeadab28c32bf9252d3ae960c79935a4cc36"}, + {file = "grpcio-1.62.2-cp38-cp38-macosx_10_10_universal2.whl", hash = "sha256:da6a7b6b938c15fa0f0568e482efaae9c3af31963eec2da4ff13a6d8ec2888e4"}, + {file = "grpcio-1.62.2-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:41955b641c34db7d84db8d306937b72bc4968eef1c401bea73081a8d6c3d8033"}, + {file = "grpcio-1.62.2-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c772f225483905f675cb36a025969eef9712f4698364ecd3a63093760deea1bc"}, + {file = "grpcio-1.62.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:07ce1f775d37ca18c7a141300e5b71539690efa1f51fe17f812ca85b5e73262f"}, + {file = "grpcio-1.62.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:26f415f40f4a93579fd648f48dca1c13dfacdfd0290f4a30f9b9aeb745026811"}, + {file = "grpcio-1.62.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:db707e3685ff16fc1eccad68527d072ac8bdd2e390f6daa97bc394ea7de4acea"}, + {file = "grpcio-1.62.2-cp38-cp38-win32.whl", hash = "sha256:589ea8e75de5fd6df387de53af6c9189c5231e212b9aa306b6b0d4f07520fbb9"}, + {file = "grpcio-1.62.2-cp38-cp38-win_amd64.whl", hash = "sha256:3c3ed41f4d7a3aabf0f01ecc70d6b5d00ce1800d4af652a549de3f7cf35c4abd"}, + {file = "grpcio-1.62.2-cp39-cp39-linux_armv7l.whl", hash = "sha256:162ccf61499c893831b8437120600290a99c0bc1ce7b51f2c8d21ec87ff6af8b"}, + {file = "grpcio-1.62.2-cp39-cp39-macosx_10_10_universal2.whl", hash = "sha256:f27246d7da7d7e3bd8612f63785a7b0c39a244cf14b8dd9dd2f2fab939f2d7f1"}, + {file = "grpcio-1.62.2-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:2507006c8a478f19e99b6fe36a2464696b89d40d88f34e4b709abe57e1337467"}, + {file = "grpcio-1.62.2-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a90ac47a8ce934e2c8d71e317d2f9e7e6aaceb2d199de940ce2c2eb611b8c0f4"}, + {file = "grpcio-1.62.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:99701979bcaaa7de8d5f60476487c5df8f27483624f1f7e300ff4669ee44d1f2"}, + {file = "grpcio-1.62.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:af7dc3f7a44f10863b1b0ecab4078f0a00f561aae1edbd01fd03ad4dcf61c9e9"}, + {file = "grpcio-1.62.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:fa63245271920786f4cb44dcada4983a3516be8f470924528cf658731864c14b"}, + {file = "grpcio-1.62.2-cp39-cp39-win32.whl", hash = "sha256:c6ad9c39704256ed91a1cffc1379d63f7d0278d6a0bad06b0330f5d30291e3a3"}, + {file = "grpcio-1.62.2-cp39-cp39-win_amd64.whl", hash = "sha256:16da954692fd61aa4941fbeda405a756cd96b97b5d95ca58a92547bba2c1624f"}, + {file = "grpcio-1.62.2.tar.gz", hash = "sha256:c77618071d96b7a8be2c10701a98537823b9c65ba256c0b9067e0594cdbd954d"}, ] [package.extras] -protobuf = ["grpcio-tools (>=1.62.1)"] +protobuf = ["grpcio-tools (>=1.62.2)"] [[package]] name = "grpcio-reflection" -version = "1.62.1" +version = "1.62.2" description = "Standard Protobuf Reflection Service for gRPC" optional = false python-versions = ">=3.6" files = [ - {file = "grpcio-reflection-1.62.1.tar.gz", hash = "sha256:abd453001991871031315ef2d82affe93080c0433fa3a007be34bf427e28a88a"}, - {file = "grpcio_reflection-1.62.1-py3-none-any.whl", hash = "sha256:3eff85f74b6b40f8e6116e8363da1efccf775b7a063d2c6fd12c190bbb9676ed"}, + {file = "grpcio-reflection-1.62.2.tar.gz", hash = "sha256:2dd44806d68d0006636529bda573012b19a42281478c2d051cdaaebb91e2516c"}, + {file = "grpcio_reflection-1.62.2-py3-none-any.whl", hash = "sha256:68e8dff3617a9afaf7c462c688f7ca62b55323f497c662abf9965f2953508885"}, ] [package.dependencies] -grpcio = ">=1.62.1" +grpcio = ">=1.62.2" protobuf = ">=4.21.6" [[package]] name = "grpcio-status" -version = "1.62.1" +version = "1.62.2" description = "Status proto mapping for gRPC" optional = false python-versions = ">=3.6" files = [ - {file = "grpcio-status-1.62.1.tar.gz", hash = "sha256:3431c8abbab0054912c41df5c72f03ddf3b7a67be8a287bb3c18a3456f96ff77"}, - {file = "grpcio_status-1.62.1-py3-none-any.whl", hash = "sha256:af0c3ab85da31669f21749e8d53d669c061ebc6ce5637be49a46edcb7aa8ab17"}, + {file = "grpcio-status-1.62.2.tar.gz", hash = "sha256:62e1bfcb02025a1cd73732a2d33672d3e9d0df4d21c12c51e0bbcaf09bab742a"}, + {file = "grpcio_status-1.62.2-py3-none-any.whl", hash = "sha256:206ddf0eb36bc99b033f03b2c8e95d319f0044defae9b41ae21408e7e0cda48f"}, ] [package.dependencies] googleapis-common-protos = ">=1.5.5" -grpcio = ">=1.62.1" +grpcio = ">=1.62.2" protobuf = ">=4.21.6" [[package]] name = "grpcio-tools" -version = "1.62.1" +version = "1.62.2" description = "Protobuf code generator for gRPC" optional = false python-versions = ">=3.7" files = [ - {file = "grpcio-tools-1.62.1.tar.gz", hash = "sha256:a4991e5ee8a97ab791296d3bf7e8700b1445635cc1828cc98df945ca1802d7f2"}, - {file = "grpcio_tools-1.62.1-cp310-cp310-linux_armv7l.whl", hash = "sha256:f2b404bcae7e2ef9b0b9803b2a95119eb7507e6dc80ea4a64a78be052c30cebc"}, - {file = "grpcio_tools-1.62.1-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:fdd987a580b4474769adfd40144486f54bcc73838d5ec5d3647a17883ea78e76"}, - {file = "grpcio_tools-1.62.1-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:07af1a6442e2313cff22af93c2c4dd37ae32b5239b38e0d99e2cbf93de65429f"}, - {file = "grpcio_tools-1.62.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:41384c9ee18e61ef20cad2774ef71bd8854b63efce263b5177aa06fccb84df1f"}, - {file = "grpcio_tools-1.62.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5c38006f7702d2ff52122e4c77a47348709374050c76216e84b30a9f06e45afa"}, - {file = "grpcio_tools-1.62.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:08fecc3c5b4e6dd3278f2b9d12837e423c7dcff551ca1e587018b4a0fc5f8019"}, - {file = "grpcio_tools-1.62.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a01e8dcd0f041f6fa6d815c54a2017d032950e310c41d514a8bc041e872c4d12"}, - {file = "grpcio_tools-1.62.1-cp310-cp310-win32.whl", hash = "sha256:dd933b8e0b3c13fe3543d58f849a6a5e0d7987688cb6801834278378c724f695"}, - {file = "grpcio_tools-1.62.1-cp310-cp310-win_amd64.whl", hash = "sha256:2b04844a9382f1bde4b4174e476e654ab3976168d2469cb4b29e352f4f35a5aa"}, - {file = "grpcio_tools-1.62.1-cp311-cp311-linux_armv7l.whl", hash = "sha256:024380536ba71a96cdf736f0954f6ad03f5da609c09edbcc2ca02fdd639e0eed"}, - {file = "grpcio_tools-1.62.1-cp311-cp311-macosx_10_10_universal2.whl", hash = "sha256:21f14b99e0cd38ad56754cc0b62b2bf3cf75f9f7fc40647da54669e0da0726fe"}, - {file = "grpcio_tools-1.62.1-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:975ac5fb482c23f3608c16e06a43c8bab4d79c2e2564cdbc25cf753c6e998775"}, - {file = "grpcio_tools-1.62.1-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:50739aaab0c8076ad5957204e71f2e0c9876e11fd8338f7f09de12c2d75163c5"}, - {file = "grpcio_tools-1.62.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:598c54318f0326cf5020aa43fc95a15e933aba4a71943d3bff2677d2d21ddfa1"}, - {file = "grpcio_tools-1.62.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:f309bdb33a61f8e049480d41498ee2e525cfb5e959958b326abfdf552bf9b9cb"}, - {file = "grpcio_tools-1.62.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:f358effd3c11d66c150e0227f983d54a5cd30e14038566dadcf25f9f6844e6e8"}, - {file = "grpcio_tools-1.62.1-cp311-cp311-win32.whl", hash = "sha256:b76aead9b73f1650a091870fe4e9ed15ac4d8ed136f962042367255199c23594"}, - {file = "grpcio_tools-1.62.1-cp311-cp311-win_amd64.whl", hash = "sha256:d66a5d47eaa427039752fa0a83a425ff2a487b6a0ac30556fd3be2f3a27a0130"}, - {file = "grpcio_tools-1.62.1-cp312-cp312-linux_armv7l.whl", hash = "sha256:575535d039b97d63e6a9abee626d6c7cd47bd8cb73dd00a5c84a98254a2164a4"}, - {file = "grpcio_tools-1.62.1-cp312-cp312-macosx_10_10_universal2.whl", hash = "sha256:22644c90e43d1a888477899af917979e17364fdd6e9bbb92679cd6a54c4d36c3"}, - {file = "grpcio_tools-1.62.1-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:156d3e1b227c16e903003a56881dbe60e40f2b4bd66f0bc3b27c53e466e6384d"}, - {file = "grpcio_tools-1.62.1-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5ad7c5691625a85327e5b683443baf73ae790fd5afc938252041ed5cd665e377"}, - {file = "grpcio_tools-1.62.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0e140bbc08eea8abf51c0274f45fb1e8350220e64758998d7f3c7f985a0b2496"}, - {file = "grpcio_tools-1.62.1-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:7444fcab861911525470d398e5638b70d5cbea3b4674a3de92b5c58c5c515d4d"}, - {file = "grpcio_tools-1.62.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:e643cd14a5d1e59865cba68a5a6f0175d987f36c5f4cb0db80dee9ed60b4c174"}, - {file = "grpcio_tools-1.62.1-cp312-cp312-win32.whl", hash = "sha256:1344a773d2caa9bb7fbea7e879b84f33740c808c34a5bd2a2768e526117a6b44"}, - {file = "grpcio_tools-1.62.1-cp312-cp312-win_amd64.whl", hash = "sha256:2eea1db3748b2f37b4dce84d8e0c15d9bc811094807cabafe7b0ea47f424dfd5"}, - {file = "grpcio_tools-1.62.1-cp37-cp37m-linux_armv7l.whl", hash = "sha256:45d2e6cf04d27286b6f73e6e20ba3f0a1f6d8f5535e5dcb1356200419bb457f4"}, - {file = "grpcio_tools-1.62.1-cp37-cp37m-macosx_10_10_universal2.whl", hash = "sha256:46ae58e6926773e7315e9005f0f17aacedbc0895a8752bec087d24efa2f1fb21"}, - {file = "grpcio_tools-1.62.1-cp37-cp37m-manylinux_2_17_aarch64.whl", hash = "sha256:4c28086df31478023a36f45e50767872ab3aed2419afff09814cb61c88b77db4"}, - {file = "grpcio_tools-1.62.1-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a4fba5b339f4797548591036c9481e6895bf920fab7d3dc664d2697f8fb7c0bf"}, - {file = "grpcio_tools-1.62.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:23eb3d47f78f509fcd201749b1f1e44b76f447913f7fbb3b8bae20f109086295"}, - {file = "grpcio_tools-1.62.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:fd5d47707bd6bc2b707ece765c362d2a1d2e8f6cd92b04c99fab49a929f3610c"}, - {file = "grpcio_tools-1.62.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:d1924a6a943df7c73b9ef0048302327c75962b567451479710da729ead241228"}, - {file = "grpcio_tools-1.62.1-cp37-cp37m-win_amd64.whl", hash = "sha256:fe71ca30aabe42591e84ecb9694c0297dc699cc20c5b24d2cb267fb0fc01f947"}, - {file = "grpcio_tools-1.62.1-cp38-cp38-linux_armv7l.whl", hash = "sha256:1819fd055c1ae672d1d725ec75eefd1f700c18acba0ed9332202be31d69c401d"}, - {file = "grpcio_tools-1.62.1-cp38-cp38-macosx_10_10_universal2.whl", hash = "sha256:5dbe1f7481dd14b6d477b4bace96d275090bc7636b9883975a08b802c94e7b78"}, - {file = "grpcio_tools-1.62.1-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:771c051c5ece27ad03e4f2e33624a925f0ad636c01757ab7dbb04a37964af4ba"}, - {file = "grpcio_tools-1.62.1-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:98209c438b38b6f1276dbc27b1c04e346a75bfaafe72a25a548f2dc5ce71d226"}, - {file = "grpcio_tools-1.62.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2152308e5321cb90fb45aaa84d03d6dedb19735a8779aaf36c624f97b831842d"}, - {file = "grpcio_tools-1.62.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:ed1f27dc2b2262c8b8d9036276619c1bb18791311c16ccbf1f31b660f2aad7cf"}, - {file = "grpcio_tools-1.62.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:2744947b6c5e907af21133431809ccca535a037356864e32c122efed8cb9de1f"}, - {file = "grpcio_tools-1.62.1-cp38-cp38-win32.whl", hash = "sha256:13b20e269d14ad629ff9a2c9a2450f3dbb119d5948de63b27ffe624fa7aea85a"}, - {file = "grpcio_tools-1.62.1-cp38-cp38-win_amd64.whl", hash = "sha256:999823758e9eacd0095863d06cd6d388be769f80c9abb65cdb11c4f2cfce3fea"}, - {file = "grpcio_tools-1.62.1-cp39-cp39-linux_armv7l.whl", hash = "sha256:941f8a5c31986053e75fa466bcfa743c2bf1b513b7978cf1f4ab4e96a8219d27"}, - {file = "grpcio_tools-1.62.1-cp39-cp39-macosx_10_10_universal2.whl", hash = "sha256:b9c02c88c77ef6057c6cbeea8922d7c2424aabf46bfc40ddf42a32765ba91061"}, - {file = "grpcio_tools-1.62.1-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:6abd4eb3ccb444383a40156139acc3aaa73745d395139cb6bc8e2a3429e1e627"}, - {file = "grpcio_tools-1.62.1-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:449503213d142f8470b331a1c2f346f8457f16c7fe20f531bc2500e271f7c14c"}, - {file = "grpcio_tools-1.62.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9a11bcf609d00cfc9baed77ab308223cabc1f0b22a05774a26dd4c94c0c80f1f"}, - {file = "grpcio_tools-1.62.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:5d7bdea33354b55acf40bb4dd3ba7324d6f1ef6b4a1a4da0807591f8c7e87b9a"}, - {file = "grpcio_tools-1.62.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:d03b645852d605f43003020e78fe6d573cae6ee6b944193e36b8b317e7549a20"}, - {file = "grpcio_tools-1.62.1-cp39-cp39-win32.whl", hash = "sha256:52b185dfc3bf32e70929310367dbc66185afba60492a6a75a9b1141d407e160c"}, - {file = "grpcio_tools-1.62.1-cp39-cp39-win_amd64.whl", hash = "sha256:63a273b70896d3640b7a883eb4a080c3c263d91662d870a2e9c84b7bbd978e7b"}, + {file = "grpcio-tools-1.62.2.tar.gz", hash = "sha256:5fd5e1582b678e6b941ee5f5809340be5e0724691df5299aae8226640f94e18f"}, + {file = "grpcio_tools-1.62.2-cp310-cp310-linux_armv7l.whl", hash = "sha256:1679b4903aed2dc5bd8cb22a452225b05dc8470a076f14fd703581efc0740cdb"}, + {file = "grpcio_tools-1.62.2-cp310-cp310-macosx_12_0_universal2.whl", hash = "sha256:9d41e0e47dd075c075bb8f103422968a65dd0d8dc8613288f573ae91eb1053ba"}, + {file = "grpcio_tools-1.62.2-cp310-cp310-manylinux_2_17_aarch64.whl", hash = "sha256:987e774f74296842bbffd55ea8826370f70c499e5b5f71a8cf3103838b6ee9c3"}, + {file = "grpcio_tools-1.62.2-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:40cd4eeea4b25bcb6903b82930d579027d034ba944393c4751cdefd9c49e6989"}, + {file = "grpcio_tools-1.62.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b6746bc823958499a3cf8963cc1de00072962fb5e629f26d658882d3f4c35095"}, + {file = "grpcio_tools-1.62.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:2ed775e844566ce9ce089be9a81a8b928623b8ee5820f5e4d58c1a9d33dfc5ae"}, + {file = "grpcio_tools-1.62.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:bdc5dd3f57b5368d5d661d5d3703bcaa38bceca59d25955dff66244dbc987271"}, + {file = "grpcio_tools-1.62.2-cp310-cp310-win32.whl", hash = "sha256:3a8d6f07e64c0c7756f4e0c4781d9d5a2b9cc9cbd28f7032a6fb8d4f847d0445"}, + {file = "grpcio_tools-1.62.2-cp310-cp310-win_amd64.whl", hash = "sha256:e33b59fb3efdddeb97ded988a871710033e8638534c826567738d3edce528752"}, + {file = "grpcio_tools-1.62.2-cp311-cp311-linux_armv7l.whl", hash = "sha256:472505d030135d73afe4143b0873efe0dcb385bd6d847553b4f3afe07679af00"}, + {file = "grpcio_tools-1.62.2-cp311-cp311-macosx_10_10_universal2.whl", hash = "sha256:ec674b4440ef4311ac1245a709e87b36aca493ddc6850eebe0b278d1f2b6e7d1"}, + {file = "grpcio_tools-1.62.2-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:184b4174d4bd82089d706e8223e46c42390a6ebac191073b9772abc77308f9fa"}, + {file = "grpcio_tools-1.62.2-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c195d74fe98541178ece7a50dad2197d43991e0f77372b9a88da438be2486f12"}, + {file = "grpcio_tools-1.62.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a34d97c62e61bfe9e6cff0410fe144ac8cca2fc979ad0be46b7edf026339d161"}, + {file = "grpcio_tools-1.62.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:cbb8453ae83a1db2452b7fe0f4b78e4a8dd32be0f2b2b73591ae620d4d784d3d"}, + {file = "grpcio_tools-1.62.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:4f989e5cebead3ae92c6abf6bf7b19949e1563a776aea896ac5933f143f0c45d"}, + {file = "grpcio_tools-1.62.2-cp311-cp311-win32.whl", hash = "sha256:c48fabe40b9170f4e3d7dd2c252e4f1ff395dc24e49ac15fc724b1b6f11724da"}, + {file = "grpcio_tools-1.62.2-cp311-cp311-win_amd64.whl", hash = "sha256:8c616d0ad872e3780693fce6a3ac8ef00fc0963e6d7815ce9dcfae68ba0fc287"}, + {file = "grpcio_tools-1.62.2-cp312-cp312-linux_armv7l.whl", hash = "sha256:10cc3321704ecd17c93cf68c99c35467a8a97ffaaed53207e9b2da6ae0308ee1"}, + {file = "grpcio_tools-1.62.2-cp312-cp312-macosx_10_10_universal2.whl", hash = "sha256:9be84ff6d47fd61462be7523b49d7ba01adf67ce4e1447eae37721ab32464dd8"}, + {file = "grpcio_tools-1.62.2-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:d82f681c9a9d933a9d8068e8e382977768e7779ddb8870fa0cf918d8250d1532"}, + {file = "grpcio_tools-1.62.2-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:04c607029ae3660fb1624ed273811ffe09d57d84287d37e63b5b802a35897329"}, + {file = "grpcio_tools-1.62.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:72b61332f1b439c14cbd3815174a8f1d35067a02047c32decd406b3a09bb9890"}, + {file = "grpcio_tools-1.62.2-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:8214820990d01b52845f9fbcb92d2b7384a0c321b303e3ac614c219dc7d1d3af"}, + {file = "grpcio_tools-1.62.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:462e0ab8dd7c7b70bfd6e3195eebc177549ede5cf3189814850c76f9a340d7ce"}, + {file = "grpcio_tools-1.62.2-cp312-cp312-win32.whl", hash = "sha256:fa107460c842e4c1a6266150881694fefd4f33baa544ea9489601810c2210ef8"}, + {file = "grpcio_tools-1.62.2-cp312-cp312-win_amd64.whl", hash = "sha256:759c60f24c33a181bbbc1232a6752f9b49fbb1583312a4917e2b389fea0fb0f2"}, + {file = "grpcio_tools-1.62.2-cp37-cp37m-linux_armv7l.whl", hash = "sha256:45db5da2bcfa88f2b86b57ef35daaae85c60bd6754a051d35d9449c959925b57"}, + {file = "grpcio_tools-1.62.2-cp37-cp37m-macosx_10_10_universal2.whl", hash = "sha256:ab84bae88597133f6ea7a2bdc57b2fda98a266fe8d8d4763652cbefd20e73ad7"}, + {file = "grpcio_tools-1.62.2-cp37-cp37m-manylinux_2_17_aarch64.whl", hash = "sha256:7a49bccae1c7d154b78e991885c3111c9ad8c8fa98e91233de425718f47c6139"}, + {file = "grpcio_tools-1.62.2-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a7e439476b29d6dac363b321781a113794397afceeb97dad85349db5f1cb5e9a"}, + {file = "grpcio_tools-1.62.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7ea369c4d1567d1acdf69c8ea74144f4ccad9e545df7f9a4fc64c94fa7684ba3"}, + {file = "grpcio_tools-1.62.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:4f955702dc4b530696375251319d05223b729ed24e8673c2129f7a75d2caefbb"}, + {file = "grpcio_tools-1.62.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:3708a747aa4b6b505727282ca887041174e146ae030ebcadaf4c1d346858df62"}, + {file = "grpcio_tools-1.62.2-cp37-cp37m-win_amd64.whl", hash = "sha256:2ce149ea55eadb486a7fb75a20f63ef3ac065ee6a0240ed25f3549ce7954c653"}, + {file = "grpcio_tools-1.62.2-cp38-cp38-linux_armv7l.whl", hash = "sha256:58cbb24b3fa6ae35aa9c210fcea3a51aa5fef0cd25618eb4fd94f746d5a9b703"}, + {file = "grpcio_tools-1.62.2-cp38-cp38-macosx_10_10_universal2.whl", hash = "sha256:6413581e14a80e0b4532577766cf0586de4dd33766a31b3eb5374a746771c07d"}, + {file = "grpcio_tools-1.62.2-cp38-cp38-manylinux_2_17_aarch64.whl", hash = "sha256:47117c8a7e861382470d0e22d336e5a91fdc5f851d1db44fa784b9acea190d87"}, + {file = "grpcio_tools-1.62.2-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9f1ba79a253df9e553d20319c615fa2b429684580fa042dba618d7f6649ac7e4"}, + {file = "grpcio_tools-1.62.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:04a394cf5e51ba9be412eb9f6c482b6270bd81016e033e8eb7d21b8cc28fe8b5"}, + {file = "grpcio_tools-1.62.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:3c53b221378b035ae2f1881cbc3aca42a6075a8e90e1a342c2f205eb1d1aa6a1"}, + {file = "grpcio_tools-1.62.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:c384c838b34d1b67068e51b5bbe49caa6aa3633acd158f1ab16b5da8d226bc53"}, + {file = "grpcio_tools-1.62.2-cp38-cp38-win32.whl", hash = "sha256:19ea69e41c3565932aa28a202d1875ec56786aea46a2eab54a3b28e8a27f9517"}, + {file = "grpcio_tools-1.62.2-cp38-cp38-win_amd64.whl", hash = "sha256:1d768a5c07279a4c461ebf52d0cec1c6ca85c6291c71ec2703fe3c3e7e28e8c4"}, + {file = "grpcio_tools-1.62.2-cp39-cp39-linux_armv7l.whl", hash = "sha256:5b07b5874187e170edfbd7aa2ca3a54ebf3b2952487653e8c0b0d83601c33035"}, + {file = "grpcio_tools-1.62.2-cp39-cp39-macosx_10_10_universal2.whl", hash = "sha256:d58389fe8be206ddfb4fa703db1e24c956856fcb9a81da62b13577b3a8f7fda7"}, + {file = "grpcio_tools-1.62.2-cp39-cp39-manylinux_2_17_aarch64.whl", hash = "sha256:7d8b4e00c3d7237b92260fc18a561cd81f1da82e8be100db1b7d816250defc66"}, + {file = "grpcio_tools-1.62.2-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1fe08d2038f2b7c53259b5c49e0ad08c8e0ce2b548d8185993e7ef67e8592cca"}, + {file = "grpcio_tools-1.62.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:19216e1fb26dbe23d12a810517e1b3fbb8d4f98b1a3fbebeec9d93a79f092de4"}, + {file = "grpcio_tools-1.62.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:b8574469ecc4ff41d6bb95f44e0297cdb0d95bade388552a9a444db9cd7485cd"}, + {file = "grpcio_tools-1.62.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:4f6f32d39283ea834a493fccf0ebe9cfddee7577bdcc27736ad4be1732a36399"}, + {file = "grpcio_tools-1.62.2-cp39-cp39-win32.whl", hash = "sha256:76eb459bdf3fb666e01883270beee18f3f11ed44488486b61cd210b4e0e17cc1"}, + {file = "grpcio_tools-1.62.2-cp39-cp39-win_amd64.whl", hash = "sha256:217c2ee6a7ce519a55958b8622e21804f6fdb774db08c322f4c9536c35fdce7c"}, ] [package.dependencies] -grpcio = ">=1.62.1" +grpcio = ">=1.62.2" protobuf = ">=4.21.6,<5.0dev" setuptools = "*" @@ -935,6 +932,20 @@ files = [ {file = "iniconfig-2.0.0.tar.gz", hash = "sha256:2d91e135bf72d31a410b17c16da610a82cb55f6b0477d1a902134b24a455b8b3"}, ] +[[package]] +name = "intel-openmp" +version = "2021.4.0" +description = "Intel OpenMP* Runtime Library" +optional = true +python-versions = "*" +files = [ + {file = "intel_openmp-2021.4.0-py2.py3-none-macosx_10_15_x86_64.macosx_11_0_x86_64.whl", hash = "sha256:41c01e266a7fdb631a7609191709322da2bbf24b252ba763f125dd651bcc7675"}, + {file = "intel_openmp-2021.4.0-py2.py3-none-manylinux1_i686.whl", hash = "sha256:3b921236a38384e2016f0f3d65af6732cf2c12918087128a9163225451e776f2"}, + {file = "intel_openmp-2021.4.0-py2.py3-none-manylinux1_x86_64.whl", hash = "sha256:e2240ab8d01472fed04f3544a878cda5da16c26232b7ea1b59132dbfb48b186e"}, + {file = "intel_openmp-2021.4.0-py2.py3-none-win32.whl", hash = "sha256:6e863d8fd3d7e8ef389d52cf97a50fe2afe1a19247e8c0d168ce021546f96fc9"}, + {file = "intel_openmp-2021.4.0-py2.py3-none-win_amd64.whl", hash = "sha256:eef4c8bcc8acefd7f5cd3b9384dbf73d59e2c99fc56545712ded913f43c4a94f"}, +] + [[package]] name = "interegular" version = "0.3.3" @@ -1143,6 +1154,24 @@ files = [ {file = "MarkupSafe-2.1.5.tar.gz", hash = "sha256:d283d37a890ba4c1ae73ffadf8046435c76e7bc2247bbb63c00bd1a709c6544b"}, ] +[[package]] +name = "mkl" +version = "2021.4.0" +description = "Intel® oneAPI Math Kernel Library" +optional = true +python-versions = "*" +files = [ + {file = "mkl-2021.4.0-py2.py3-none-macosx_10_15_x86_64.macosx_11_0_x86_64.whl", hash = "sha256:67460f5cd7e30e405b54d70d1ed3ca78118370b65f7327d495e9c8847705e2fb"}, + {file = "mkl-2021.4.0-py2.py3-none-manylinux1_i686.whl", hash = "sha256:636d07d90e68ccc9630c654d47ce9fdeb036bb46e2b193b3a9ac8cfea683cce5"}, + {file = "mkl-2021.4.0-py2.py3-none-manylinux1_x86_64.whl", hash = "sha256:398dbf2b0d12acaf54117a5210e8f191827f373d362d796091d161f610c1ebfb"}, + {file = "mkl-2021.4.0-py2.py3-none-win32.whl", hash = "sha256:439c640b269a5668134e3dcbcea4350459c4a8bc46469669b2d67e07e3d330e8"}, + {file = "mkl-2021.4.0-py2.py3-none-win_amd64.whl", hash = "sha256:ceef3cafce4c009dd25f65d7ad0d833a0fbadc3d8903991ec92351fe5de1e718"}, +] + +[package.dependencies] +intel-openmp = "==2021.*" +tbb = "==2021.*" + [[package]] name = "mpmath" version = "1.3.0" @@ -1261,27 +1290,31 @@ files = [ [[package]] name = "multiprocess" -version = "0.70.16" +version = "0.70.15" description = "better multiprocessing and multithreading in Python" optional = true -python-versions = ">=3.8" +python-versions = ">=3.7" files = [ - {file = "multiprocess-0.70.16-pp310-pypy310_pp73-macosx_10_13_x86_64.whl", hash = "sha256:476887be10e2f59ff183c006af746cb6f1fd0eadcfd4ef49e605cbe2659920ee"}, - {file = "multiprocess-0.70.16-pp310-pypy310_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:d951bed82c8f73929ac82c61f01a7b5ce8f3e5ef40f5b52553b4f547ce2b08ec"}, - {file = "multiprocess-0.70.16-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:37b55f71c07e2d741374998c043b9520b626a8dddc8b3129222ca4f1a06ef67a"}, - {file = "multiprocess-0.70.16-pp38-pypy38_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:ba8c31889abf4511c7308a8c52bb4a30b9d590e7f58523302ba00237702ca054"}, - {file = "multiprocess-0.70.16-pp39-pypy39_pp73-macosx_10_13_x86_64.whl", hash = "sha256:0dfd078c306e08d46d7a8d06fb120313d87aa43af60d66da43ffff40b44d2f41"}, - {file = "multiprocess-0.70.16-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:e7b9d0f307cd9bd50851afaac0dba2cb6c44449efff697df7c7645f7d3f2be3a"}, - {file = "multiprocess-0.70.16-py310-none-any.whl", hash = "sha256:c4a9944c67bd49f823687463660a2d6daae94c289adff97e0f9d696ba6371d02"}, - {file = "multiprocess-0.70.16-py311-none-any.whl", hash = "sha256:af4cabb0dac72abfb1e794fa7855c325fd2b55a10a44628a3c1ad3311c04127a"}, - {file = "multiprocess-0.70.16-py312-none-any.whl", hash = "sha256:fc0544c531920dde3b00c29863377f87e1632601092ea2daca74e4beb40faa2e"}, - {file = "multiprocess-0.70.16-py38-none-any.whl", hash = "sha256:a71d82033454891091a226dfc319d0cfa8019a4e888ef9ca910372a446de4435"}, - {file = "multiprocess-0.70.16-py39-none-any.whl", hash = "sha256:a0bafd3ae1b732eac64be2e72038231c1ba97724b60b09400d68f229fcc2fbf3"}, - {file = "multiprocess-0.70.16.tar.gz", hash = "sha256:161af703d4652a0e1410be6abccecde4a7ddffd19341be0a7011b94aeb171ac1"}, + {file = "multiprocess-0.70.15-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:aa36c7ed16f508091438687fe9baa393a7a8e206731d321e443745e743a0d4e5"}, + {file = "multiprocess-0.70.15-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:20e024018c46d0d1602024c613007ac948f9754659e3853b0aa705e83f6931d8"}, + {file = "multiprocess-0.70.15-pp37-pypy37_pp73-manylinux_2_24_i686.whl", hash = "sha256:e576062981c91f0fe8a463c3d52506e598dfc51320a8dd8d78b987dfca91c5db"}, + {file = "multiprocess-0.70.15-pp37-pypy37_pp73-manylinux_2_24_x86_64.whl", hash = "sha256:e73f497e6696a0f5433ada2b3d599ae733b87a6e8b008e387c62ac9127add177"}, + {file = "multiprocess-0.70.15-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:73db2e7b32dcc7f9b0f075c2ffa45c90b6729d3f1805f27e88534c8d321a1be5"}, + {file = "multiprocess-0.70.15-pp38-pypy38_pp73-manylinux_2_24_i686.whl", hash = "sha256:4271647bd8a49c28ecd6eb56a7fdbd3c212c45529ad5303b40b3c65fc6928e5f"}, + {file = "multiprocess-0.70.15-pp38-pypy38_pp73-manylinux_2_24_x86_64.whl", hash = "sha256:cf981fb998d6ec3208cb14f0cf2e9e80216e834f5d51fd09ebc937c32b960902"}, + {file = "multiprocess-0.70.15-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:18f9f2c7063346d1617bd1684fdcae8d33380ae96b99427260f562e1a1228b67"}, + {file = "multiprocess-0.70.15-pp39-pypy39_pp73-manylinux_2_24_i686.whl", hash = "sha256:0eac53214d664c49a34695e5824872db4006b1a465edd7459a251809c3773370"}, + {file = "multiprocess-0.70.15-pp39-pypy39_pp73-manylinux_2_24_x86_64.whl", hash = "sha256:1a51dd34096db47fb21fa2b839e615b051d51b97af9a67afbcdaa67186b44883"}, + {file = "multiprocess-0.70.15-py310-none-any.whl", hash = "sha256:7dd58e33235e83cf09d625e55cffd7b0f0eede7ee9223cdd666a87624f60c21a"}, + {file = "multiprocess-0.70.15-py311-none-any.whl", hash = "sha256:134f89053d82c9ed3b73edd3a2531eb791e602d4f4156fc92a79259590bd9670"}, + {file = "multiprocess-0.70.15-py37-none-any.whl", hash = "sha256:f7d4a1629bccb433114c3b4885f69eccc200994323c80f6feee73b0edc9199c5"}, + {file = "multiprocess-0.70.15-py38-none-any.whl", hash = "sha256:bee9afba476c91f9ebee7beeee0601face9eff67d822e893f9a893725fbd6316"}, + {file = "multiprocess-0.70.15-py39-none-any.whl", hash = "sha256:3e0953f5d52b4c76f1c973eaf8214554d146f2be5decb48e928e55c7a2d19338"}, + {file = "multiprocess-0.70.15.tar.gz", hash = "sha256:f20eed3036c0ef477b07a4177cf7c1ba520d9a2677870a4f47fe026f0cd6787e"}, ] [package.dependencies] -dill = ">=0.3.8" +dill = ">=0.3.7" [[package]] name = "nest-asyncio" @@ -1502,12 +1535,13 @@ nvidia-nvjitlink-cu12 = "*" [[package]] name = "nvidia-nccl-cu12" -version = "2.19.3" +version = "2.20.5" description = "NVIDIA Collective Communication Library (NCCL) Runtime" optional = true python-versions = ">=3" files = [ - {file = "nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl", hash = "sha256:a9734707a2c96443331c1e48c717024aa6678a0e2a4cb66b2c364d18cee6b48d"}, + {file = "nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_aarch64.whl", hash = "sha256:1fc150d5c3250b170b29410ba682384b14581db722b2531b0d8d33c595f33d01"}, + {file = "nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl", hash = "sha256:057f6bf9685f75215d0c53bf3ac4a10b3e6578351de307abad9e18a99182af56"}, ] [[package]] @@ -1920,19 +1954,33 @@ xmp = ["defusedxml"] [[package]] name = "pluggy" -version = "1.4.0" +version = "1.5.0" description = "plugin and hook calling mechanisms for python" optional = false python-versions = ">=3.8" files = [ - {file = "pluggy-1.4.0-py3-none-any.whl", hash = "sha256:7db9f7b503d67d1c5b95f59773ebb58a8c1c288129a88665838012cfb07b8981"}, - {file = "pluggy-1.4.0.tar.gz", hash = "sha256:8c85c2876142a764e5b7548e7d9a0e0ddb46f5185161049a79b7e974454223be"}, + {file = "pluggy-1.5.0-py3-none-any.whl", hash = "sha256:44e1ad92c8ca002de6377e165f3e0f1be63266ab4d554740532335b9d75ea669"}, + {file = "pluggy-1.5.0.tar.gz", hash = "sha256:2cffa88e94fdc978c4c574f15f9e59b7f4201d439195c3715ca9e2486f1d0cf1"}, ] [package.extras] dev = ["pre-commit", "tox"] testing = ["pytest", "pytest-benchmark"] +[[package]] +name = "prometheus-client" +version = "0.20.0" +description = "Python client for the Prometheus monitoring system." +optional = false +python-versions = ">=3.8" +files = [ + {file = "prometheus_client-0.20.0-py3-none-any.whl", hash = "sha256:cde524a85bce83ca359cc837f28b8c0db5cac7aa653a588fd7e84ba061c329e7"}, + {file = "prometheus_client-0.20.0.tar.gz", hash = "sha256:287629d00b147a32dcb2be0b9df905da599b2d82f80377083ec8463309a4bb89"}, +] + +[package.extras] +twisted = ["twisted"] + [[package]] name = "protobuf" version = "4.25.3" @@ -1981,79 +2029,79 @@ files = [ [package.extras] test = ["enum34", "ipaddress", "mock", "pywin32", "wmi"] +[[package]] +name = "py-cpuinfo" +version = "9.0.0" +description = "Get CPU info with pure Python" +optional = false +python-versions = "*" +files = [ + {file = "py-cpuinfo-9.0.0.tar.gz", hash = "sha256:3cdbbf3fac90dc6f118bfd64384f309edeadd902d7c8fb17f02ffa1fc3f49690"}, + {file = "py_cpuinfo-9.0.0-py3-none-any.whl", hash = "sha256:859625bc251f64e21f077d099d4162689c762b5d6a4c3c97553d56241c9674d5"}, +] + [[package]] name = "pyarrow" -version = "15.0.2" +version = "16.0.0" description = "Python library for Apache Arrow" optional = true python-versions = ">=3.8" files = [ - {file = "pyarrow-15.0.2-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:88b340f0a1d05b5ccc3d2d986279045655b1fe8e41aba6ca44ea28da0d1455d8"}, - {file = "pyarrow-15.0.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:eaa8f96cecf32da508e6c7f69bb8401f03745c050c1dd42ec2596f2e98deecac"}, - {file = "pyarrow-15.0.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:23c6753ed4f6adb8461e7c383e418391b8d8453c5d67e17f416c3a5d5709afbd"}, - {file = "pyarrow-15.0.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f639c059035011db8c0497e541a8a45d98a58dbe34dc8fadd0ef128f2cee46e5"}, - {file = "pyarrow-15.0.2-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:290e36a59a0993e9a5224ed2fb3e53375770f07379a0ea03ee2fce2e6d30b423"}, - {file = "pyarrow-15.0.2-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:06c2bb2a98bc792f040bef31ad3e9be6a63d0cb39189227c08a7d955db96816e"}, - {file = "pyarrow-15.0.2-cp310-cp310-win_amd64.whl", hash = "sha256:f7a197f3670606a960ddc12adbe8075cea5f707ad7bf0dffa09637fdbb89f76c"}, - {file = "pyarrow-15.0.2-cp311-cp311-macosx_10_15_x86_64.whl", hash = "sha256:5f8bc839ea36b1f99984c78e06e7a06054693dc2af8920f6fb416b5bca9944e4"}, - {file = "pyarrow-15.0.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:f5e81dfb4e519baa6b4c80410421528c214427e77ca0ea9461eb4097c328fa33"}, - {file = "pyarrow-15.0.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3a4f240852b302a7af4646c8bfe9950c4691a419847001178662a98915fd7ee7"}, - {file = "pyarrow-15.0.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4e7d9cfb5a1e648e172428c7a42b744610956f3b70f524aa3a6c02a448ba853e"}, - {file = "pyarrow-15.0.2-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:2d4f905209de70c0eb5b2de6763104d5a9a37430f137678edfb9a675bac9cd98"}, - {file = "pyarrow-15.0.2-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:90adb99e8ce5f36fbecbbc422e7dcbcbed07d985eed6062e459e23f9e71fd197"}, - {file = "pyarrow-15.0.2-cp311-cp311-win_amd64.whl", hash = "sha256:b116e7fd7889294cbd24eb90cd9bdd3850be3738d61297855a71ac3b8124ee38"}, - {file = "pyarrow-15.0.2-cp312-cp312-macosx_10_15_x86_64.whl", hash = "sha256:25335e6f1f07fdaa026a61c758ee7d19ce824a866b27bba744348fa73bb5a440"}, - {file = "pyarrow-15.0.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:90f19e976d9c3d8e73c80be84ddbe2f830b6304e4c576349d9360e335cd627fc"}, - {file = "pyarrow-15.0.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a22366249bf5fd40ddacc4f03cd3160f2d7c247692945afb1899bab8a140ddfb"}, - {file = "pyarrow-15.0.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c2a335198f886b07e4b5ea16d08ee06557e07db54a8400cc0d03c7f6a22f785f"}, - {file = "pyarrow-15.0.2-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:3e6d459c0c22f0b9c810a3917a1de3ee704b021a5fb8b3bacf968eece6df098f"}, - {file = "pyarrow-15.0.2-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:033b7cad32198754d93465dcfb71d0ba7cb7cd5c9afd7052cab7214676eec38b"}, - {file = "pyarrow-15.0.2-cp312-cp312-win_amd64.whl", hash = "sha256:29850d050379d6e8b5a693098f4de7fd6a2bea4365bfd073d7c57c57b95041ee"}, - {file = "pyarrow-15.0.2-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:7167107d7fb6dcadb375b4b691b7e316f4368f39f6f45405a05535d7ad5e5058"}, - {file = "pyarrow-15.0.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:e85241b44cc3d365ef950432a1b3bd44ac54626f37b2e3a0cc89c20e45dfd8bf"}, - {file = "pyarrow-15.0.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:248723e4ed3255fcd73edcecc209744d58a9ca852e4cf3d2577811b6d4b59818"}, - {file = "pyarrow-15.0.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ff3bdfe6f1b81ca5b73b70a8d482d37a766433823e0c21e22d1d7dde76ca33f"}, - {file = "pyarrow-15.0.2-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:f3d77463dee7e9f284ef42d341689b459a63ff2e75cee2b9302058d0d98fe142"}, - {file = "pyarrow-15.0.2-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:8c1faf2482fb89766e79745670cbca04e7018497d85be9242d5350cba21357e1"}, - {file = "pyarrow-15.0.2-cp38-cp38-win_amd64.whl", hash = "sha256:28f3016958a8e45a1069303a4a4f6a7d4910643fc08adb1e2e4a7ff056272ad3"}, - {file = "pyarrow-15.0.2-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:89722cb64286ab3d4daf168386f6968c126057b8c7ec3ef96302e81d8cdb8ae4"}, - {file = "pyarrow-15.0.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:cd0ba387705044b3ac77b1b317165c0498299b08261d8122c96051024f953cd5"}, - {file = "pyarrow-15.0.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ad2459bf1f22b6a5cdcc27ebfd99307d5526b62d217b984b9f5c974651398832"}, - {file = "pyarrow-15.0.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:58922e4bfece8b02abf7159f1f53a8f4d9f8e08f2d988109126c17c3bb261f22"}, - {file = "pyarrow-15.0.2-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:adccc81d3dc0478ea0b498807b39a8d41628fa9210729b2f718b78cb997c7c91"}, - {file = "pyarrow-15.0.2-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:8bd2baa5fe531571847983f36a30ddbf65261ef23e496862ece83bdceb70420d"}, - {file = "pyarrow-15.0.2-cp39-cp39-win_amd64.whl", hash = "sha256:6669799a1d4ca9da9c7e06ef48368320f5856f36f9a4dd31a11839dda3f6cc8c"}, - {file = "pyarrow-15.0.2.tar.gz", hash = "sha256:9c9bc803cb3b7bfacc1e96ffbfd923601065d9d3f911179d81e72d99fd74a3d9"}, + {file = "pyarrow-16.0.0-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:22a1fdb1254e5095d629e29cd1ea98ed04b4bbfd8e42cc670a6b639ccc208b60"}, + {file = "pyarrow-16.0.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:574a00260a4ed9d118a14770edbd440b848fcae5a3024128be9d0274dbcaf858"}, + {file = "pyarrow-16.0.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c0815d0ddb733b8c1b53a05827a91f1b8bde6240f3b20bf9ba5d650eb9b89cdf"}, + {file = "pyarrow-16.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:df0080339387b5d30de31e0a149c0c11a827a10c82f0c67d9afae3981d1aabb7"}, + {file = "pyarrow-16.0.0-cp310-cp310-manylinux_2_28_aarch64.whl", hash = "sha256:edf38cce0bf0dcf726e074159c60516447e4474904c0033f018c1f33d7dac6c5"}, + {file = "pyarrow-16.0.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:91d28f9a40f1264eab2af7905a4d95320ac2f287891e9c8b0035f264fe3c3a4b"}, + {file = "pyarrow-16.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:99af421ee451a78884d7faea23816c429e263bd3618b22d38e7992c9ce2a7ad9"}, + {file = "pyarrow-16.0.0-cp311-cp311-macosx_10_15_x86_64.whl", hash = "sha256:d22d0941e6c7bafddf5f4c0662e46f2075850f1c044bf1a03150dd9e189427ce"}, + {file = "pyarrow-16.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:266ddb7e823f03733c15adc8b5078db2df6980f9aa93d6bb57ece615df4e0ba7"}, + {file = "pyarrow-16.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5cc23090224b6594f5a92d26ad47465af47c1d9c079dd4a0061ae39551889efe"}, + {file = "pyarrow-16.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:56850a0afe9ef37249d5387355449c0f94d12ff7994af88f16803a26d38f2016"}, + {file = "pyarrow-16.0.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:705db70d3e2293c2f6f8e84874b5b775f690465798f66e94bb2c07bab0a6bb55"}, + {file = "pyarrow-16.0.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:5448564754c154997bc09e95a44b81b9e31ae918a86c0fcb35c4aa4922756f55"}, + {file = "pyarrow-16.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:729f7b262aa620c9df8b9967db96c1575e4cfc8c25d078a06968e527b8d6ec05"}, + {file = "pyarrow-16.0.0-cp312-cp312-macosx_10_15_x86_64.whl", hash = "sha256:fb8065dbc0d051bf2ae2453af0484d99a43135cadabacf0af588a3be81fbbb9b"}, + {file = "pyarrow-16.0.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:20ce707d9aa390593ea93218b19d0eadab56390311cb87aad32c9a869b0e958c"}, + {file = "pyarrow-16.0.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5823275c8addbbb50cd4e6a6839952682a33255b447277e37a6f518d6972f4e1"}, + {file = "pyarrow-16.0.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1ab8b9050752b16a8b53fcd9853bf07d8daf19093533e990085168f40c64d978"}, + {file = "pyarrow-16.0.0-cp312-cp312-manylinux_2_28_aarch64.whl", hash = "sha256:42e56557bc7c5c10d3e42c3b32f6cff649a29d637e8f4e8b311d334cc4326730"}, + {file = "pyarrow-16.0.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:2a7abdee4a4a7cfa239e2e8d721224c4b34ffe69a0ca7981354fe03c1328789b"}, + {file = "pyarrow-16.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:ef2f309b68396bcc5a354106741d333494d6a0d3e1951271849787109f0229a6"}, + {file = "pyarrow-16.0.0-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:ed66e5217b4526fa3585b5e39b0b82f501b88a10d36bd0d2a4d8aa7b5a48e2df"}, + {file = "pyarrow-16.0.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:cc8814310486f2a73c661ba8354540f17eef51e1b6dd090b93e3419d3a097b3a"}, + {file = "pyarrow-16.0.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3c2f5e239db7ed43e0ad2baf46a6465f89c824cc703f38ef0fde927d8e0955f7"}, + {file = "pyarrow-16.0.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f293e92d1db251447cb028ae12f7bc47526e4649c3a9924c8376cab4ad6b98bd"}, + {file = "pyarrow-16.0.0-cp38-cp38-manylinux_2_28_aarch64.whl", hash = "sha256:dd9334a07b6dc21afe0857aa31842365a62eca664e415a3f9536e3a8bb832c07"}, + {file = "pyarrow-16.0.0-cp38-cp38-manylinux_2_28_x86_64.whl", hash = "sha256:d91073d1e2fef2c121154680e2ba7e35ecf8d4969cc0af1fa6f14a8675858159"}, + {file = "pyarrow-16.0.0-cp38-cp38-win_amd64.whl", hash = "sha256:71d52561cd7aefd22cf52538f262850b0cc9e4ec50af2aaa601da3a16ef48877"}, + {file = "pyarrow-16.0.0-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:b93c9a50b965ee0bf4fef65e53b758a7e8dcc0c2d86cebcc037aaaf1b306ecc0"}, + {file = "pyarrow-16.0.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:d831690844706e374c455fba2fb8cfcb7b797bfe53ceda4b54334316e1ac4fa4"}, + {file = "pyarrow-16.0.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:35692ce8ad0b8c666aa60f83950957096d92f2a9d8d7deda93fb835e6053307e"}, + {file = "pyarrow-16.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9dd3151d098e56f16a8389c1247137f9e4c22720b01c6f3aa6dec29a99b74d80"}, + {file = "pyarrow-16.0.0-cp39-cp39-manylinux_2_28_aarch64.whl", hash = "sha256:bd40467bdb3cbaf2044ed7a6f7f251c8f941c8b31275aaaf88e746c4f3ca4a7a"}, + {file = "pyarrow-16.0.0-cp39-cp39-manylinux_2_28_x86_64.whl", hash = "sha256:00a1dcb22ad4ceb8af87f7bd30cc3354788776c417f493089e0a0af981bc8d80"}, + {file = "pyarrow-16.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:fda9a7cebd1b1d46c97b511f60f73a5b766a6de4c5236f144f41a5d5afec1f35"}, + {file = "pyarrow-16.0.0.tar.gz", hash = "sha256:59bb1f1edbbf4114c72415f039f1359f1a57d166a331c3229788ccbfbb31689a"}, ] [package.dependencies] -numpy = ">=1.16.6,<2" - -[[package]] -name = "pyarrow-hotfix" -version = "0.6" -description = "" -optional = true -python-versions = ">=3.5" -files = [ - {file = "pyarrow_hotfix-0.6-py3-none-any.whl", hash = "sha256:dcc9ae2d220dff0083be6a9aa8e0cdee5182ad358d4931fce825c545e5c89178"}, - {file = "pyarrow_hotfix-0.6.tar.gz", hash = "sha256:79d3e030f7ff890d408a100ac16d6f00b14d44a502d7897cd9fc3e3a534e9945"}, -] +numpy = ">=1.16.6" [[package]] name = "pydantic" -version = "2.7.0" +version = "2.7.1" description = "Data validation using Python type hints" optional = true python-versions = ">=3.8" files = [ - {file = "pydantic-2.7.0-py3-none-any.whl", hash = "sha256:9dee74a271705f14f9a1567671d144a851c675b072736f0a7b2608fd9e495352"}, - {file = "pydantic-2.7.0.tar.gz", hash = "sha256:b5ecdd42262ca2462e2624793551e80911a1e989f462910bb81aef974b4bb383"}, + {file = "pydantic-2.7.1-py3-none-any.whl", hash = "sha256:e029badca45266732a9a79898a15ae2e8b14840b1eabbb25844be28f0b33f3d5"}, + {file = "pydantic-2.7.1.tar.gz", hash = "sha256:e9dbb5eada8abe4d9ae5f46b9939aead650cd2b68f249bb3a8139dbe125803cc"}, ] [package.dependencies] annotated-types = ">=0.4.0" -pydantic-core = "2.18.1" +pydantic-core = "2.18.2" typing-extensions = ">=4.6.1" [package.extras] @@ -2061,90 +2109,90 @@ email = ["email-validator (>=2.0.0)"] [[package]] name = "pydantic-core" -version = "2.18.1" +version = "2.18.2" description = "Core functionality for Pydantic validation and serialization" optional = true python-versions = ">=3.8" files = [ - {file = "pydantic_core-2.18.1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:ee9cf33e7fe14243f5ca6977658eb7d1042caaa66847daacbd2117adb258b226"}, - {file = "pydantic_core-2.18.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:6b7bbb97d82659ac8b37450c60ff2e9f97e4eb0f8a8a3645a5568b9334b08b50"}, - {file = "pydantic_core-2.18.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:df4249b579e75094f7e9bb4bd28231acf55e308bf686b952f43100a5a0be394c"}, - {file = "pydantic_core-2.18.1-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d0491006a6ad20507aec2be72e7831a42efc93193d2402018007ff827dc62926"}, - {file = "pydantic_core-2.18.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2ae80f72bb7a3e397ab37b53a2b49c62cc5496412e71bc4f1277620a7ce3f52b"}, - {file = "pydantic_core-2.18.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:58aca931bef83217fca7a390e0486ae327c4af9c3e941adb75f8772f8eeb03a1"}, - {file = "pydantic_core-2.18.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1be91ad664fc9245404a789d60cba1e91c26b1454ba136d2a1bf0c2ac0c0505a"}, - {file = "pydantic_core-2.18.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:667880321e916a8920ef49f5d50e7983792cf59f3b6079f3c9dac2b88a311d17"}, - {file = "pydantic_core-2.18.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:f7054fdc556f5421f01e39cbb767d5ec5c1139ea98c3e5b350e02e62201740c7"}, - {file = "pydantic_core-2.18.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:030e4f9516f9947f38179249778709a460a3adb516bf39b5eb9066fcfe43d0e6"}, - {file = "pydantic_core-2.18.1-cp310-none-win32.whl", hash = "sha256:2e91711e36e229978d92642bfc3546333a9127ecebb3f2761372e096395fc649"}, - {file = "pydantic_core-2.18.1-cp310-none-win_amd64.whl", hash = "sha256:9a29726f91c6cb390b3c2338f0df5cd3e216ad7a938762d11c994bb37552edb0"}, - {file = "pydantic_core-2.18.1-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:9ece8a49696669d483d206b4474c367852c44815fca23ac4e48b72b339807f80"}, - {file = "pydantic_core-2.18.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7a5d83efc109ceddb99abd2c1316298ced2adb4570410defe766851a804fcd5b"}, - {file = "pydantic_core-2.18.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5f7973c381283783cd1043a8c8f61ea5ce7a3a58b0369f0ee0ee975eaf2f2a1b"}, - {file = "pydantic_core-2.18.1-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:54c7375c62190a7845091f521add19b0f026bcf6ae674bdb89f296972272e86d"}, - {file = "pydantic_core-2.18.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:dd63cec4e26e790b70544ae5cc48d11b515b09e05fdd5eff12e3195f54b8a586"}, - {file = "pydantic_core-2.18.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:561cf62c8a3498406495cfc49eee086ed2bb186d08bcc65812b75fda42c38294"}, - {file = "pydantic_core-2.18.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:68717c38a68e37af87c4da20e08f3e27d7e4212e99e96c3d875fbf3f4812abfc"}, - {file = "pydantic_core-2.18.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:2d5728e93d28a3c63ee513d9ffbac9c5989de8c76e049dbcb5bfe4b923a9739d"}, - {file = "pydantic_core-2.18.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:f0f17814c505f07806e22b28856c59ac80cee7dd0fbb152aed273e116378f519"}, - {file = "pydantic_core-2.18.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:d816f44a51ba5175394bc6c7879ca0bd2be560b2c9e9f3411ef3a4cbe644c2e9"}, - {file = "pydantic_core-2.18.1-cp311-none-win32.whl", hash = "sha256:09f03dfc0ef8c22622eaa8608caa4a1e189cfb83ce847045eca34f690895eccb"}, - {file = "pydantic_core-2.18.1-cp311-none-win_amd64.whl", hash = "sha256:27f1009dc292f3b7ca77feb3571c537276b9aad5dd4efb471ac88a8bd09024e9"}, - {file = "pydantic_core-2.18.1-cp311-none-win_arm64.whl", hash = "sha256:48dd883db92e92519201f2b01cafa881e5f7125666141a49ffba8b9facc072b0"}, - {file = "pydantic_core-2.18.1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:b6b0e4912030c6f28bcb72b9ebe4989d6dc2eebcd2a9cdc35fefc38052dd4fe8"}, - {file = "pydantic_core-2.18.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:f3202a429fe825b699c57892d4371c74cc3456d8d71b7f35d6028c96dfecad31"}, - {file = "pydantic_core-2.18.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a3982b0a32d0a88b3907e4b0dc36809fda477f0757c59a505d4e9b455f384b8b"}, - {file = "pydantic_core-2.18.1-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:25595ac311f20e5324d1941909b0d12933f1fd2171075fcff763e90f43e92a0d"}, - {file = "pydantic_core-2.18.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:14fe73881cf8e4cbdaded8ca0aa671635b597e42447fec7060d0868b52d074e6"}, - {file = "pydantic_core-2.18.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ca976884ce34070799e4dfc6fbd68cb1d181db1eefe4a3a94798ddfb34b8867f"}, - {file = "pydantic_core-2.18.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:684d840d2c9ec5de9cb397fcb3f36d5ebb6fa0d94734f9886032dd796c1ead06"}, - {file = "pydantic_core-2.18.1-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:54764c083bbe0264f0f746cefcded6cb08fbbaaf1ad1d78fb8a4c30cff999a90"}, - {file = "pydantic_core-2.18.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:201713f2f462e5c015b343e86e68bd8a530a4f76609b33d8f0ec65d2b921712a"}, - {file = "pydantic_core-2.18.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:fd1a9edb9dd9d79fbeac1ea1f9a8dd527a6113b18d2e9bcc0d541d308dae639b"}, - {file = "pydantic_core-2.18.1-cp312-none-win32.whl", hash = "sha256:d5e6b7155b8197b329dc787356cfd2684c9d6a6b1a197f6bbf45f5555a98d411"}, - {file = "pydantic_core-2.18.1-cp312-none-win_amd64.whl", hash = "sha256:9376d83d686ec62e8b19c0ac3bf8d28d8a5981d0df290196fb6ef24d8a26f0d6"}, - {file = "pydantic_core-2.18.1-cp312-none-win_arm64.whl", hash = "sha256:c562b49c96906b4029b5685075fe1ebd3b5cc2601dfa0b9e16c2c09d6cbce048"}, - {file = "pydantic_core-2.18.1-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:3e352f0191d99fe617371096845070dee295444979efb8f27ad941227de6ad09"}, - {file = "pydantic_core-2.18.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:c0295d52b012cbe0d3059b1dba99159c3be55e632aae1999ab74ae2bd86a33d7"}, - {file = "pydantic_core-2.18.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:56823a92075780582d1ffd4489a2e61d56fd3ebb4b40b713d63f96dd92d28144"}, - {file = "pydantic_core-2.18.1-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:dd3f79e17b56741b5177bcc36307750d50ea0698df6aa82f69c7db32d968c1c2"}, - {file = "pydantic_core-2.18.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:38a5024de321d672a132b1834a66eeb7931959c59964b777e8f32dbe9523f6b1"}, - {file = "pydantic_core-2.18.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d2ce426ee691319d4767748c8e0895cfc56593d725594e415f274059bcf3cb76"}, - {file = "pydantic_core-2.18.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2adaeea59849ec0939af5c5d476935f2bab4b7f0335b0110f0f069a41024278e"}, - {file = "pydantic_core-2.18.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:9b6431559676a1079eac0f52d6d0721fb8e3c5ba43c37bc537c8c83724031feb"}, - {file = "pydantic_core-2.18.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:85233abb44bc18d16e72dc05bf13848a36f363f83757541f1a97db2f8d58cfd9"}, - {file = "pydantic_core-2.18.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:641a018af4fe48be57a2b3d7a1f0f5dbca07c1d00951d3d7463f0ac9dac66622"}, - {file = "pydantic_core-2.18.1-cp38-none-win32.whl", hash = "sha256:63d7523cd95d2fde0d28dc42968ac731b5bb1e516cc56b93a50ab293f4daeaad"}, - {file = "pydantic_core-2.18.1-cp38-none-win_amd64.whl", hash = "sha256:907a4d7720abfcb1c81619863efd47c8a85d26a257a2dbebdb87c3b847df0278"}, - {file = "pydantic_core-2.18.1-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:aad17e462f42ddbef5984d70c40bfc4146c322a2da79715932cd8976317054de"}, - {file = "pydantic_core-2.18.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:94b9769ba435b598b547c762184bcfc4783d0d4c7771b04a3b45775c3589ca44"}, - {file = "pydantic_core-2.18.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:80e0e57cc704a52fb1b48f16d5b2c8818da087dbee6f98d9bf19546930dc64b5"}, - {file = "pydantic_core-2.18.1-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:76b86e24039c35280ceee6dce7e62945eb93a5175d43689ba98360ab31eebc4a"}, - {file = "pydantic_core-2.18.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:12a05db5013ec0ca4a32cc6433f53faa2a014ec364031408540ba858c2172bb0"}, - {file = "pydantic_core-2.18.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:250ae39445cb5475e483a36b1061af1bc233de3e9ad0f4f76a71b66231b07f88"}, - {file = "pydantic_core-2.18.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a32204489259786a923e02990249c65b0f17235073149d0033efcebe80095570"}, - {file = "pydantic_core-2.18.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:6395a4435fa26519fd96fdccb77e9d00ddae9dd6c742309bd0b5610609ad7fb2"}, - {file = "pydantic_core-2.18.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:2533ad2883f001efa72f3d0e733fb846710c3af6dcdd544fe5bf14fa5fe2d7db"}, - {file = "pydantic_core-2.18.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:b560b72ed4816aee52783c66854d96157fd8175631f01ef58e894cc57c84f0f6"}, - {file = "pydantic_core-2.18.1-cp39-none-win32.whl", hash = "sha256:582cf2cead97c9e382a7f4d3b744cf0ef1a6e815e44d3aa81af3ad98762f5a9b"}, - {file = "pydantic_core-2.18.1-cp39-none-win_amd64.whl", hash = "sha256:ca71d501629d1fa50ea7fa3b08ba884fe10cefc559f5c6c8dfe9036c16e8ae89"}, - {file = "pydantic_core-2.18.1-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:e178e5b66a06ec5bf51668ec0d4ac8cfb2bdcb553b2c207d58148340efd00143"}, - {file = "pydantic_core-2.18.1-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:72722ce529a76a4637a60be18bd789d8fb871e84472490ed7ddff62d5fed620d"}, - {file = "pydantic_core-2.18.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2fe0c1ce5b129455e43f941f7a46f61f3d3861e571f2905d55cdbb8b5c6f5e2c"}, - {file = "pydantic_core-2.18.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d4284c621f06a72ce2cb55f74ea3150113d926a6eb78ab38340c08f770eb9b4d"}, - {file = "pydantic_core-2.18.1-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:1a0c3e718f4e064efde68092d9d974e39572c14e56726ecfaeebbe6544521f47"}, - {file = "pydantic_core-2.18.1-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:2027493cc44c23b598cfaf200936110433d9caa84e2c6cf487a83999638a96ac"}, - {file = "pydantic_core-2.18.1-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:76909849d1a6bffa5a07742294f3fa1d357dc917cb1fe7b470afbc3a7579d539"}, - {file = "pydantic_core-2.18.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:ee7ccc7fb7e921d767f853b47814c3048c7de536663e82fbc37f5eb0d532224b"}, - {file = "pydantic_core-2.18.1-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:ee2794111c188548a4547eccc73a6a8527fe2af6cf25e1a4ebda2fd01cdd2e60"}, - {file = "pydantic_core-2.18.1-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:a139fe9f298dc097349fb4f28c8b81cc7a202dbfba66af0e14be5cfca4ef7ce5"}, - {file = "pydantic_core-2.18.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d074b07a10c391fc5bbdcb37b2f16f20fcd9e51e10d01652ab298c0d07908ee2"}, - {file = "pydantic_core-2.18.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c69567ddbac186e8c0aadc1f324a60a564cfe25e43ef2ce81bcc4b8c3abffbae"}, - {file = "pydantic_core-2.18.1-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:baf1c7b78cddb5af00971ad5294a4583188bda1495b13760d9f03c9483bb6203"}, - {file = "pydantic_core-2.18.1-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:2684a94fdfd1b146ff10689c6e4e815f6a01141781c493b97342cdc5b06f4d5d"}, - {file = "pydantic_core-2.18.1-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:73c1bc8a86a5c9e8721a088df234265317692d0b5cd9e86e975ce3bc3db62a59"}, - {file = "pydantic_core-2.18.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:e60defc3c15defb70bb38dd605ff7e0fae5f6c9c7cbfe0ad7868582cb7e844a6"}, - {file = "pydantic_core-2.18.1.tar.gz", hash = "sha256:de9d3e8717560eb05e28739d1b35e4eac2e458553a52a301e51352a7ffc86a35"}, + {file = "pydantic_core-2.18.2-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:9e08e867b306f525802df7cd16c44ff5ebbe747ff0ca6cf3fde7f36c05a59a81"}, + {file = "pydantic_core-2.18.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:f0a21cbaa69900cbe1a2e7cad2aa74ac3cf21b10c3efb0fa0b80305274c0e8a2"}, + {file = "pydantic_core-2.18.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0680b1f1f11fda801397de52c36ce38ef1c1dc841a0927a94f226dea29c3ae3d"}, + {file = "pydantic_core-2.18.2-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:95b9d5e72481d3780ba3442eac863eae92ae43a5f3adb5b4d0a1de89d42bb250"}, + {file = "pydantic_core-2.18.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c4fcf5cd9c4b655ad666ca332b9a081112cd7a58a8b5a6ca7a3104bc950f2038"}, + {file = "pydantic_core-2.18.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9b5155ff768083cb1d62f3e143b49a8a3432e6789a3abee8acd005c3c7af1c74"}, + {file = "pydantic_core-2.18.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:553ef617b6836fc7e4df130bb851e32fe357ce36336d897fd6646d6058d980af"}, + {file = "pydantic_core-2.18.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:b89ed9eb7d616ef5714e5590e6cf7f23b02d0d539767d33561e3675d6f9e3857"}, + {file = "pydantic_core-2.18.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:75f7e9488238e920ab6204399ded280dc4c307d034f3924cd7f90a38b1829563"}, + {file = "pydantic_core-2.18.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:ef26c9e94a8c04a1b2924149a9cb081836913818e55681722d7f29af88fe7b38"}, + {file = "pydantic_core-2.18.2-cp310-none-win32.whl", hash = "sha256:182245ff6b0039e82b6bb585ed55a64d7c81c560715d1bad0cbad6dfa07b4027"}, + {file = "pydantic_core-2.18.2-cp310-none-win_amd64.whl", hash = "sha256:e23ec367a948b6d812301afc1b13f8094ab7b2c280af66ef450efc357d2ae543"}, + {file = "pydantic_core-2.18.2-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:219da3f096d50a157f33645a1cf31c0ad1fe829a92181dd1311022f986e5fbe3"}, + {file = "pydantic_core-2.18.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:cc1cfd88a64e012b74e94cd00bbe0f9c6df57049c97f02bb07d39e9c852e19a4"}, + {file = "pydantic_core-2.18.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:05b7133a6e6aeb8df37d6f413f7705a37ab4031597f64ab56384c94d98fa0e90"}, + {file = "pydantic_core-2.18.2-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:224c421235f6102e8737032483f43c1a8cfb1d2f45740c44166219599358c2cd"}, + {file = "pydantic_core-2.18.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b14d82cdb934e99dda6d9d60dc84a24379820176cc4a0d123f88df319ae9c150"}, + {file = "pydantic_core-2.18.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2728b01246a3bba6de144f9e3115b532ee44bd6cf39795194fb75491824a1413"}, + {file = "pydantic_core-2.18.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:470b94480bb5ee929f5acba6995251ada5e059a5ef3e0dfc63cca287283ebfa6"}, + {file = "pydantic_core-2.18.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:997abc4df705d1295a42f95b4eec4950a37ad8ae46d913caeee117b6b198811c"}, + {file = "pydantic_core-2.18.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:75250dbc5290e3f1a0f4618db35e51a165186f9034eff158f3d490b3fed9f8a0"}, + {file = "pydantic_core-2.18.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:4456f2dca97c425231d7315737d45239b2b51a50dc2b6f0c2bb181fce6207664"}, + {file = "pydantic_core-2.18.2-cp311-none-win32.whl", hash = "sha256:269322dcc3d8bdb69f054681edff86276b2ff972447863cf34c8b860f5188e2e"}, + {file = "pydantic_core-2.18.2-cp311-none-win_amd64.whl", hash = "sha256:800d60565aec896f25bc3cfa56d2277d52d5182af08162f7954f938c06dc4ee3"}, + {file = "pydantic_core-2.18.2-cp311-none-win_arm64.whl", hash = "sha256:1404c69d6a676245199767ba4f633cce5f4ad4181f9d0ccb0577e1f66cf4c46d"}, + {file = "pydantic_core-2.18.2-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:fb2bd7be70c0fe4dfd32c951bc813d9fe6ebcbfdd15a07527796c8204bd36242"}, + {file = "pydantic_core-2.18.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:6132dd3bd52838acddca05a72aafb6eab6536aa145e923bb50f45e78b7251043"}, + {file = "pydantic_core-2.18.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d7d904828195733c183d20a54230c0df0eb46ec746ea1a666730787353e87182"}, + {file = "pydantic_core-2.18.2-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:c9bd70772c720142be1020eac55f8143a34ec9f82d75a8e7a07852023e46617f"}, + {file = "pydantic_core-2.18.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2b8ed04b3582771764538f7ee7001b02e1170223cf9b75dff0bc698fadb00cf3"}, + {file = "pydantic_core-2.18.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e6dac87ddb34aaec85f873d737e9d06a3555a1cc1a8e0c44b7f8d5daeb89d86f"}, + {file = "pydantic_core-2.18.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7ca4ae5a27ad7a4ee5170aebce1574b375de390bc01284f87b18d43a3984df72"}, + {file = "pydantic_core-2.18.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:886eec03591b7cf058467a70a87733b35f44707bd86cf64a615584fd72488b7c"}, + {file = "pydantic_core-2.18.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:ca7b0c1f1c983e064caa85f3792dd2fe3526b3505378874afa84baf662e12241"}, + {file = "pydantic_core-2.18.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:4b4356d3538c3649337df4074e81b85f0616b79731fe22dd11b99499b2ebbdf3"}, + {file = "pydantic_core-2.18.2-cp312-none-win32.whl", hash = "sha256:8b172601454f2d7701121bbec3425dd71efcb787a027edf49724c9cefc14c038"}, + {file = "pydantic_core-2.18.2-cp312-none-win_amd64.whl", hash = "sha256:b1bd7e47b1558ea872bd16c8502c414f9e90dcf12f1395129d7bb42a09a95438"}, + {file = "pydantic_core-2.18.2-cp312-none-win_arm64.whl", hash = "sha256:98758d627ff397e752bc339272c14c98199c613f922d4a384ddc07526c86a2ec"}, + {file = "pydantic_core-2.18.2-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:9fdad8e35f278b2c3eb77cbdc5c0a49dada440657bf738d6905ce106dc1de439"}, + {file = "pydantic_core-2.18.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:1d90c3265ae107f91a4f279f4d6f6f1d4907ac76c6868b27dc7fb33688cfb347"}, + {file = "pydantic_core-2.18.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:390193c770399861d8df9670fb0d1874f330c79caaca4642332df7c682bf6b91"}, + {file = "pydantic_core-2.18.2-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:82d5d4d78e4448683cb467897fe24e2b74bb7b973a541ea1dcfec1d3cbce39fb"}, + {file = "pydantic_core-2.18.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4774f3184d2ef3e14e8693194f661dea5a4d6ca4e3dc8e39786d33a94865cefd"}, + {file = "pydantic_core-2.18.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d4d938ec0adf5167cb335acb25a4ee69a8107e4984f8fbd2e897021d9e4ca21b"}, + {file = "pydantic_core-2.18.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e0e8b1be28239fc64a88a8189d1df7fad8be8c1ae47fcc33e43d4be15f99cc70"}, + {file = "pydantic_core-2.18.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:868649da93e5a3d5eacc2b5b3b9235c98ccdbfd443832f31e075f54419e1b96b"}, + {file = "pydantic_core-2.18.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:78363590ef93d5d226ba21a90a03ea89a20738ee5b7da83d771d283fd8a56761"}, + {file = "pydantic_core-2.18.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:852e966fbd035a6468fc0a3496589b45e2208ec7ca95c26470a54daed82a0788"}, + {file = "pydantic_core-2.18.2-cp38-none-win32.whl", hash = "sha256:6a46e22a707e7ad4484ac9ee9f290f9d501df45954184e23fc29408dfad61350"}, + {file = "pydantic_core-2.18.2-cp38-none-win_amd64.whl", hash = "sha256:d91cb5ea8b11607cc757675051f61b3d93f15eca3cefb3e6c704a5d6e8440f4e"}, + {file = "pydantic_core-2.18.2-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:ae0a8a797a5e56c053610fa7be147993fe50960fa43609ff2a9552b0e07013e8"}, + {file = "pydantic_core-2.18.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:042473b6280246b1dbf530559246f6842b56119c2926d1e52b631bdc46075f2a"}, + {file = "pydantic_core-2.18.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1a388a77e629b9ec814c1b1e6b3b595fe521d2cdc625fcca26fbc2d44c816804"}, + {file = "pydantic_core-2.18.2-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e25add29b8f3b233ae90ccef2d902d0ae0432eb0d45370fe315d1a5cf231004b"}, + {file = "pydantic_core-2.18.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f459a5ce8434614dfd39bbebf1041952ae01da6bed9855008cb33b875cb024c0"}, + {file = "pydantic_core-2.18.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:eff2de745698eb46eeb51193a9f41d67d834d50e424aef27df2fcdee1b153845"}, + {file = "pydantic_core-2.18.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a8309f67285bdfe65c372ea3722b7a5642680f3dba538566340a9d36e920b5f0"}, + {file = "pydantic_core-2.18.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:f93a8a2e3938ff656a7c1bc57193b1319960ac015b6e87d76c76bf14fe0244b4"}, + {file = "pydantic_core-2.18.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:22057013c8c1e272eb8d0eebc796701167d8377441ec894a8fed1af64a0bf399"}, + {file = "pydantic_core-2.18.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:cfeecd1ac6cc1fb2692c3d5110781c965aabd4ec5d32799773ca7b1456ac636b"}, + {file = "pydantic_core-2.18.2-cp39-none-win32.whl", hash = "sha256:0d69b4c2f6bb3e130dba60d34c0845ba31b69babdd3f78f7c0c8fae5021a253e"}, + {file = "pydantic_core-2.18.2-cp39-none-win_amd64.whl", hash = "sha256:d9319e499827271b09b4e411905b24a426b8fb69464dfa1696258f53a3334641"}, + {file = "pydantic_core-2.18.2-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:a1874c6dd4113308bd0eb568418e6114b252afe44319ead2b4081e9b9521fe75"}, + {file = "pydantic_core-2.18.2-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:ccdd111c03bfd3666bd2472b674c6899550e09e9f298954cfc896ab92b5b0e6d"}, + {file = "pydantic_core-2.18.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e18609ceaa6eed63753037fc06ebb16041d17d28199ae5aba0052c51449650a9"}, + {file = "pydantic_core-2.18.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6e5c584d357c4e2baf0ff7baf44f4994be121e16a2c88918a5817331fc7599d7"}, + {file = "pydantic_core-2.18.2-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:43f0f463cf89ace478de71a318b1b4f05ebc456a9b9300d027b4b57c1a2064fb"}, + {file = "pydantic_core-2.18.2-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:e1b395e58b10b73b07b7cf740d728dd4ff9365ac46c18751bf8b3d8cca8f625a"}, + {file = "pydantic_core-2.18.2-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:0098300eebb1c837271d3d1a2cd2911e7c11b396eac9661655ee524a7f10587b"}, + {file = "pydantic_core-2.18.2-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:36789b70d613fbac0a25bb07ab3d9dba4d2e38af609c020cf4d888d165ee0bf3"}, + {file = "pydantic_core-2.18.2-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:3f9a801e7c8f1ef8718da265bba008fa121243dfe37c1cea17840b0944dfd72c"}, + {file = "pydantic_core-2.18.2-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:3a6515ebc6e69d85502b4951d89131ca4e036078ea35533bb76327f8424531ce"}, + {file = "pydantic_core-2.18.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:20aca1e2298c56ececfd8ed159ae4dde2df0781988c97ef77d5c16ff4bd5b400"}, + {file = "pydantic_core-2.18.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:223ee893d77a310a0391dca6df00f70bbc2f36a71a895cecd9a0e762dc37b349"}, + {file = "pydantic_core-2.18.2-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:2334ce8c673ee93a1d6a65bd90327588387ba073c17e61bf19b4fd97d688d63c"}, + {file = "pydantic_core-2.18.2-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:cbca948f2d14b09d20268cda7b0367723d79063f26c4ffc523af9042cad95592"}, + {file = "pydantic_core-2.18.2-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:b3ef08e20ec49e02d5c6717a91bb5af9b20f1805583cb0adfe9ba2c6b505b5ae"}, + {file = "pydantic_core-2.18.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:c6fdc8627910eed0c01aed6a390a252fe3ea6d472ee70fdde56273f198938374"}, + {file = "pydantic_core-2.18.2.tar.gz", hash = "sha256:2e29d20810dfc3043ee13ac7d9e25105799817683348823f305ab3f349b9386e"}, ] [package.dependencies] @@ -2222,6 +2270,7 @@ files = [ {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"}, {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"}, {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"}, + {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a08c6f0fe150303c1c6b71ebcd7213c2858041a7e01975da3a99aed1e7a378ef"}, {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"}, {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"}, {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"}, @@ -2258,13 +2307,13 @@ files = [ [[package]] name = "referencing" -version = "0.34.0" +version = "0.35.0" description = "JSON Referencing + Python" optional = true python-versions = ">=3.8" files = [ - {file = "referencing-0.34.0-py3-none-any.whl", hash = "sha256:d53ae300ceddd3169f1ffa9caf2cb7b769e92657e4fafb23d34b93679116dfd4"}, - {file = "referencing-0.34.0.tar.gz", hash = "sha256:5773bd84ef41799a5a8ca72dc34590c041eb01bf9aa02632b4a973fb0181a844"}, + {file = "referencing-0.35.0-py3-none-any.whl", hash = "sha256:8080727b30e364e5783152903672df9b6b091c926a146a759080b62ca3126cd6"}, + {file = "referencing-0.35.0.tar.gz", hash = "sha256:191e936b0c696d0af17ad7430a3dc68e88bc11be6514f4757dc890f04ab05889"}, ] [package.dependencies] @@ -2273,104 +2322,90 @@ rpds-py = ">=0.7.0" [[package]] name = "regex" -version = "2024.4.16" +version = "2024.4.28" description = "Alternative regular expression module, to replace re." optional = false -python-versions = ">=3.7" +python-versions = ">=3.8" files = [ - {file = "regex-2024.4.16-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:fb83cc090eac63c006871fd24db5e30a1f282faa46328572661c0a24a2323a08"}, - {file = "regex-2024.4.16-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8c91e1763696c0eb66340c4df98623c2d4e77d0746b8f8f2bee2c6883fd1fe18"}, - {file = "regex-2024.4.16-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:10188fe732dec829c7acca7422cdd1bf57d853c7199d5a9e96bb4d40db239c73"}, - {file = "regex-2024.4.16-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:956b58d692f235cfbf5b4f3abd6d99bf102f161ccfe20d2fd0904f51c72c4c66"}, - {file = "regex-2024.4.16-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a70b51f55fd954d1f194271695821dd62054d949efd6368d8be64edd37f55c86"}, - {file = "regex-2024.4.16-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5c02fcd2bf45162280613d2e4a1ca3ac558ff921ae4e308ecb307650d3a6ee51"}, - {file = "regex-2024.4.16-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c4ed75ea6892a56896d78f11006161eea52c45a14994794bcfa1654430984b22"}, - {file = "regex-2024.4.16-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bd727ad276bb91928879f3aa6396c9a1d34e5e180dce40578421a691eeb77f47"}, - {file = "regex-2024.4.16-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:7cbc5d9e8a1781e7be17da67b92580d6ce4dcef5819c1b1b89f49d9678cc278c"}, - {file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:78fddb22b9ef810b63ef341c9fcf6455232d97cfe03938cbc29e2672c436670e"}, - {file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:445ca8d3c5a01309633a0c9db57150312a181146315693273e35d936472df912"}, - {file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:95399831a206211d6bc40224af1c635cb8790ddd5c7493e0bd03b85711076a53"}, - {file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:7731728b6568fc286d86745f27f07266de49603a6fdc4d19c87e8c247be452af"}, - {file = "regex-2024.4.16-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:4facc913e10bdba42ec0aee76d029aedda628161a7ce4116b16680a0413f658a"}, - {file = "regex-2024.4.16-cp310-cp310-win32.whl", hash = "sha256:911742856ce98d879acbea33fcc03c1d8dc1106234c5e7d068932c945db209c0"}, - {file = "regex-2024.4.16-cp310-cp310-win_amd64.whl", hash = "sha256:e0a2df336d1135a0b3a67f3bbf78a75f69562c1199ed9935372b82215cddd6e2"}, - {file = "regex-2024.4.16-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:1210365faba7c2150451eb78ec5687871c796b0f1fa701bfd2a4a25420482d26"}, - {file = "regex-2024.4.16-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:9ab40412f8cd6f615bfedea40c8bf0407d41bf83b96f6fc9ff34976d6b7037fd"}, - {file = "regex-2024.4.16-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:fd80d1280d473500d8086d104962a82d77bfbf2b118053824b7be28cd5a79ea5"}, - {file = "regex-2024.4.16-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7bb966fdd9217e53abf824f437a5a2d643a38d4fd5fd0ca711b9da683d452969"}, - {file = "regex-2024.4.16-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:20b7a68444f536365af42a75ccecb7ab41a896a04acf58432db9e206f4e525d6"}, - {file = "regex-2024.4.16-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b74586dd0b039c62416034f811d7ee62810174bb70dffcca6439f5236249eb09"}, - {file = "regex-2024.4.16-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0c8290b44d8b0af4e77048646c10c6e3aa583c1ca67f3b5ffb6e06cf0c6f0f89"}, - {file = "regex-2024.4.16-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f2d80a6749724b37853ece57988b39c4e79d2b5fe2869a86e8aeae3bbeef9eb0"}, - {file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:3a1018e97aeb24e4f939afcd88211ace472ba566efc5bdf53fd8fd7f41fa7170"}, - {file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:8d015604ee6204e76569d2f44e5a210728fa917115bef0d102f4107e622b08d5"}, - {file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:3d5ac5234fb5053850d79dd8eb1015cb0d7d9ed951fa37aa9e6249a19aa4f336"}, - {file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:0a38d151e2cdd66d16dab550c22f9521ba79761423b87c01dae0a6e9add79c0d"}, - {file = "regex-2024.4.16-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:159dc4e59a159cb8e4e8f8961eb1fa5d58f93cb1acd1701d8aff38d45e1a84a6"}, - {file = "regex-2024.4.16-cp311-cp311-win32.whl", hash = "sha256:ba2336d6548dee3117520545cfe44dc28a250aa091f8281d28804aa8d707d93d"}, - {file = "regex-2024.4.16-cp311-cp311-win_amd64.whl", hash = "sha256:8f83b6fd3dc3ba94d2b22717f9c8b8512354fd95221ac661784df2769ea9bba9"}, - {file = "regex-2024.4.16-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:80b696e8972b81edf0af2a259e1b2a4a661f818fae22e5fa4fa1a995fb4a40fd"}, - {file = "regex-2024.4.16-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:d61ae114d2a2311f61d90c2ef1358518e8f05eafda76eaf9c772a077e0b465ec"}, - {file = "regex-2024.4.16-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8ba6745440b9a27336443b0c285d705ce73adb9ec90e2f2004c64d95ab5a7598"}, - {file = "regex-2024.4.16-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6295004b2dd37b0835ea5c14a33e00e8cfa3c4add4d587b77287825f3418d310"}, - {file = "regex-2024.4.16-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4aba818dcc7263852aabb172ec27b71d2abca02a593b95fa79351b2774eb1d2b"}, - {file = "regex-2024.4.16-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d0800631e565c47520aaa04ae38b96abc5196fe8b4aa9bd864445bd2b5848a7a"}, - {file = "regex-2024.4.16-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:08dea89f859c3df48a440dbdcd7b7155bc675f2fa2ec8c521d02dc69e877db70"}, - {file = "regex-2024.4.16-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:eeaa0b5328b785abc344acc6241cffde50dc394a0644a968add75fcefe15b9d4"}, - {file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:4e819a806420bc010489f4e741b3036071aba209f2e0989d4750b08b12a9343f"}, - {file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:c2d0e7cbb6341e830adcbfa2479fdeebbfbb328f11edd6b5675674e7a1e37730"}, - {file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:91797b98f5e34b6a49f54be33f72e2fb658018ae532be2f79f7c63b4ae225145"}, - {file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:d2da13568eff02b30fd54fccd1e042a70fe920d816616fda4bf54ec705668d81"}, - {file = "regex-2024.4.16-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:370c68dc5570b394cbaadff50e64d705f64debed30573e5c313c360689b6aadc"}, - {file = "regex-2024.4.16-cp312-cp312-win32.whl", hash = "sha256:904c883cf10a975b02ab3478bce652f0f5346a2c28d0a8521d97bb23c323cc8b"}, - {file = "regex-2024.4.16-cp312-cp312-win_amd64.whl", hash = "sha256:785c071c982dce54d44ea0b79cd6dfafddeccdd98cfa5f7b86ef69b381b457d9"}, - {file = "regex-2024.4.16-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:e2f142b45c6fed48166faeb4303b4b58c9fcd827da63f4cf0a123c3480ae11fb"}, - {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e87ab229332ceb127a165612d839ab87795972102cb9830e5f12b8c9a5c1b508"}, - {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:81500ed5af2090b4a9157a59dbc89873a25c33db1bb9a8cf123837dcc9765047"}, - {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b340cccad138ecb363324aa26893963dcabb02bb25e440ebdf42e30963f1a4e0"}, - {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2c72608e70f053643437bd2be0608f7f1c46d4022e4104d76826f0839199347a"}, - {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a01fe2305e6232ef3e8f40bfc0f0f3a04def9aab514910fa4203bafbc0bb4682"}, - {file = "regex-2024.4.16-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:03576e3a423d19dda13e55598f0fd507b5d660d42c51b02df4e0d97824fdcae3"}, - {file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:549c3584993772e25f02d0656ac48abdda73169fe347263948cf2b1cead622f3"}, - {file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:34422d5a69a60b7e9a07a690094e824b66f5ddc662a5fc600d65b7c174a05f04"}, - {file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:5f580c651a72b75c39e311343fe6875d6f58cf51c471a97f15a938d9fe4e0d37"}, - {file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:3399dd8a7495bbb2bacd59b84840eef9057826c664472e86c91d675d007137f5"}, - {file = "regex-2024.4.16-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:8d1f86f3f4e2388aa3310b50694ac44daefbd1681def26b4519bd050a398dc5a"}, - {file = "regex-2024.4.16-cp37-cp37m-win32.whl", hash = "sha256:dd5acc0a7d38fdc7a3a6fd3ad14c880819008ecb3379626e56b163165162cc46"}, - {file = "regex-2024.4.16-cp37-cp37m-win_amd64.whl", hash = "sha256:ba8122e3bb94ecda29a8de4cf889f600171424ea586847aa92c334772d200331"}, - {file = "regex-2024.4.16-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:743deffdf3b3481da32e8a96887e2aa945ec6685af1cfe2bcc292638c9ba2f48"}, - {file = "regex-2024.4.16-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:7571f19f4a3fd00af9341c7801d1ad1967fc9c3f5e62402683047e7166b9f2b4"}, - {file = "regex-2024.4.16-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:df79012ebf6f4efb8d307b1328226aef24ca446b3ff8d0e30202d7ebcb977a8c"}, - {file = "regex-2024.4.16-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e757d475953269fbf4b441207bb7dbdd1c43180711b6208e129b637792ac0b93"}, - {file = "regex-2024.4.16-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4313ab9bf6a81206c8ac28fdfcddc0435299dc88cad12cc6305fd0e78b81f9e4"}, - {file = "regex-2024.4.16-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d83c2bc678453646f1a18f8db1e927a2d3f4935031b9ad8a76e56760461105dd"}, - {file = "regex-2024.4.16-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9df1bfef97db938469ef0a7354b2d591a2d438bc497b2c489471bec0e6baf7c4"}, - {file = "regex-2024.4.16-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:62120ed0de69b3649cc68e2965376048793f466c5a6c4370fb27c16c1beac22d"}, - {file = "regex-2024.4.16-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:c2ef6f7990b6e8758fe48ad08f7e2f66c8f11dc66e24093304b87cae9037bb4a"}, - {file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:8fc6976a3395fe4d1fbeb984adaa8ec652a1e12f36b56ec8c236e5117b585427"}, - {file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:03e68f44340528111067cecf12721c3df4811c67268b897fbe695c95f860ac42"}, - {file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:ec7e0043b91115f427998febaa2beb82c82df708168b35ece3accb610b91fac1"}, - {file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:c21fc21a4c7480479d12fd8e679b699f744f76bb05f53a1d14182b31f55aac76"}, - {file = "regex-2024.4.16-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:12f6a3f2f58bb7344751919a1876ee1b976fe08b9ffccb4bbea66f26af6017b9"}, - {file = "regex-2024.4.16-cp38-cp38-win32.whl", hash = "sha256:479595a4fbe9ed8f8f72c59717e8cf222da2e4c07b6ae5b65411e6302af9708e"}, - {file = "regex-2024.4.16-cp38-cp38-win_amd64.whl", hash = "sha256:0534b034fba6101611968fae8e856c1698da97ce2efb5c2b895fc8b9e23a5834"}, - {file = "regex-2024.4.16-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:a7ccdd1c4a3472a7533b0a7aa9ee34c9a2bef859ba86deec07aff2ad7e0c3b94"}, - {file = "regex-2024.4.16-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:6f2f017c5be19984fbbf55f8af6caba25e62c71293213f044da3ada7091a4455"}, - {file = "regex-2024.4.16-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:803b8905b52de78b173d3c1e83df0efb929621e7b7c5766c0843704d5332682f"}, - {file = "regex-2024.4.16-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:684008ec44ad275832a5a152f6e764bbe1914bea10968017b6feaecdad5736e0"}, - {file = "regex-2024.4.16-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:65436dce9fdc0aeeb0a0effe0839cb3d6a05f45aa45a4d9f9c60989beca78b9c"}, - {file = "regex-2024.4.16-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ea355eb43b11764cf799dda62c658c4d2fdb16af41f59bb1ccfec517b60bcb07"}, - {file = "regex-2024.4.16-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:98c1165f3809ce7774f05cb74e5408cd3aa93ee8573ae959a97a53db3ca3180d"}, - {file = "regex-2024.4.16-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cccc79a9be9b64c881f18305a7c715ba199e471a3973faeb7ba84172abb3f317"}, - {file = "regex-2024.4.16-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:00169caa125f35d1bca6045d65a662af0202704489fada95346cfa092ec23f39"}, - {file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:6cc38067209354e16c5609b66285af17a2863a47585bcf75285cab33d4c3b8df"}, - {file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:23cff1b267038501b179ccbbd74a821ac4a7192a1852d1d558e562b507d46013"}, - {file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:b9d320b3bf82a39f248769fc7f188e00f93526cc0fe739cfa197868633d44701"}, - {file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:89ec7f2c08937421bbbb8b48c54096fa4f88347946d4747021ad85f1b3021b3c"}, - {file = "regex-2024.4.16-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:4918fd5f8b43aa7ec031e0fef1ee02deb80b6afd49c85f0790be1dc4ce34cb50"}, - {file = "regex-2024.4.16-cp39-cp39-win32.whl", hash = "sha256:684e52023aec43bdf0250e843e1fdd6febbe831bd9d52da72333fa201aaa2335"}, - {file = "regex-2024.4.16-cp39-cp39-win_amd64.whl", hash = "sha256:e697e1c0238133589e00c244a8b676bc2cfc3ab4961318d902040d099fec7483"}, - {file = "regex-2024.4.16.tar.gz", hash = "sha256:fa454d26f2e87ad661c4f0c5a5fe4cf6aab1e307d1b94f16ffdfcb089ba685c0"}, + {file = "regex-2024.4.28-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:cd196d056b40af073d95a2879678585f0b74ad35190fac04ca67954c582c6b61"}, + {file = "regex-2024.4.28-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8bb381f777351bd534462f63e1c6afb10a7caa9fa2a421ae22c26e796fe31b1f"}, + {file = "regex-2024.4.28-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:47af45b6153522733aa6e92543938e97a70ce0900649ba626cf5aad290b737b6"}, + {file = "regex-2024.4.28-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:99d6a550425cc51c656331af0e2b1651e90eaaa23fb4acde577cf15068e2e20f"}, + {file = "regex-2024.4.28-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:bf29304a8011feb58913c382902fde3395957a47645bf848eea695839aa101b7"}, + {file = "regex-2024.4.28-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:92da587eee39a52c91aebea8b850e4e4f095fe5928d415cb7ed656b3460ae79a"}, + {file = "regex-2024.4.28-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6277d426e2f31bdbacb377d17a7475e32b2d7d1f02faaecc48d8e370c6a3ff31"}, + {file = "regex-2024.4.28-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:28e1f28d07220c0f3da0e8fcd5a115bbb53f8b55cecf9bec0c946eb9a059a94c"}, + {file = "regex-2024.4.28-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:aaa179975a64790c1f2701ac562b5eeb733946eeb036b5bcca05c8d928a62f10"}, + {file = "regex-2024.4.28-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:6f435946b7bf7a1b438b4e6b149b947c837cb23c704e780c19ba3e6855dbbdd3"}, + {file = "regex-2024.4.28-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:19d6c11bf35a6ad077eb23852827f91c804eeb71ecb85db4ee1386825b9dc4db"}, + {file = "regex-2024.4.28-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:fdae0120cddc839eb8e3c15faa8ad541cc6d906d3eb24d82fb041cfe2807bc1e"}, + {file = "regex-2024.4.28-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:e672cf9caaf669053121f1766d659a8813bd547edef6e009205378faf45c67b8"}, + {file = "regex-2024.4.28-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:f57515750d07e14743db55d59759893fdb21d2668f39e549a7d6cad5d70f9fea"}, + {file = "regex-2024.4.28-cp310-cp310-win32.whl", hash = "sha256:a1409c4eccb6981c7baabc8888d3550df518add6e06fe74fa1d9312c1838652d"}, + {file = "regex-2024.4.28-cp310-cp310-win_amd64.whl", hash = "sha256:1f687a28640f763f23f8a9801fe9e1b37338bb1ca5d564ddd41619458f1f22d1"}, + {file = "regex-2024.4.28-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:84077821c85f222362b72fdc44f7a3a13587a013a45cf14534df1cbbdc9a6796"}, + {file = "regex-2024.4.28-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b45d4503de8f4f3dc02f1d28a9b039e5504a02cc18906cfe744c11def942e9eb"}, + {file = "regex-2024.4.28-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:457c2cd5a646dd4ed536c92b535d73548fb8e216ebee602aa9f48e068fc393f3"}, + {file = "regex-2024.4.28-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2b51739ddfd013c6f657b55a508de8b9ea78b56d22b236052c3a85a675102dc6"}, + {file = "regex-2024.4.28-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:459226445c7d7454981c4c0ce0ad1a72e1e751c3e417f305722bbcee6697e06a"}, + {file = "regex-2024.4.28-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:670fa596984b08a4a769491cbdf22350431970d0112e03d7e4eeaecaafcd0fec"}, + {file = "regex-2024.4.28-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fe00f4fe11c8a521b173e6324d862ee7ee3412bf7107570c9b564fe1119b56fb"}, + {file = "regex-2024.4.28-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:36f392dc7763fe7924575475736bddf9ab9f7a66b920932d0ea50c2ded2f5636"}, + {file = "regex-2024.4.28-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:23a412b7b1a7063f81a742463f38821097b6a37ce1e5b89dd8e871d14dbfd86b"}, + {file = "regex-2024.4.28-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:f1d6e4b7b2ae3a6a9df53efbf199e4bfcff0959dbdb5fd9ced34d4407348e39a"}, + {file = "regex-2024.4.28-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:499334ad139557de97cbc4347ee921c0e2b5e9c0f009859e74f3f77918339257"}, + {file = "regex-2024.4.28-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:0940038bec2fe9e26b203d636c44d31dd8766abc1fe66262da6484bd82461ccf"}, + {file = "regex-2024.4.28-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:66372c2a01782c5fe8e04bff4a2a0121a9897e19223d9eab30c54c50b2ebeb7f"}, + {file = "regex-2024.4.28-cp311-cp311-win32.whl", hash = "sha256:c77d10ec3c1cf328b2f501ca32583625987ea0f23a0c2a49b37a39ee5c4c4630"}, + {file = "regex-2024.4.28-cp311-cp311-win_amd64.whl", hash = "sha256:fc0916c4295c64d6890a46e02d4482bb5ccf33bf1a824c0eaa9e83b148291f90"}, + {file = "regex-2024.4.28-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:08a1749f04fee2811c7617fdd46d2e46d09106fa8f475c884b65c01326eb15c5"}, + {file = "regex-2024.4.28-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b8eb28995771c087a73338f695a08c9abfdf723d185e57b97f6175c5051ff1ae"}, + {file = "regex-2024.4.28-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:dd7ef715ccb8040954d44cfeff17e6b8e9f79c8019daae2fd30a8806ef5435c0"}, + {file = "regex-2024.4.28-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fb0315a2b26fde4005a7c401707c5352df274460f2f85b209cf6024271373013"}, + {file = "regex-2024.4.28-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f2fc053228a6bd3a17a9b0a3f15c3ab3cf95727b00557e92e1cfe094b88cc662"}, + {file = "regex-2024.4.28-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7fe9739a686dc44733d52d6e4f7b9c77b285e49edf8570754b322bca6b85b4cc"}, + {file = "regex-2024.4.28-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a74fcf77d979364f9b69fcf8200849ca29a374973dc193a7317698aa37d8b01c"}, + {file = "regex-2024.4.28-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:965fd0cf4694d76f6564896b422724ec7b959ef927a7cb187fc6b3f4e4f59833"}, + {file = "regex-2024.4.28-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:2fef0b38c34ae675fcbb1b5db760d40c3fc3612cfa186e9e50df5782cac02bcd"}, + {file = "regex-2024.4.28-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:bc365ce25f6c7c5ed70e4bc674f9137f52b7dd6a125037f9132a7be52b8a252f"}, + {file = "regex-2024.4.28-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:ac69b394764bb857429b031d29d9604842bc4cbfd964d764b1af1868eeebc4f0"}, + {file = "regex-2024.4.28-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:144a1fc54765f5c5c36d6d4b073299832aa1ec6a746a6452c3ee7b46b3d3b11d"}, + {file = "regex-2024.4.28-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:2630ca4e152c221072fd4a56d4622b5ada876f668ecd24d5ab62544ae6793ed6"}, + {file = "regex-2024.4.28-cp312-cp312-win32.whl", hash = "sha256:7f3502f03b4da52bbe8ba962621daa846f38489cae5c4a7b5d738f15f6443d17"}, + {file = "regex-2024.4.28-cp312-cp312-win_amd64.whl", hash = "sha256:0dd3f69098511e71880fb00f5815db9ed0ef62c05775395968299cb400aeab82"}, + {file = "regex-2024.4.28-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:374f690e1dd0dbdcddea4a5c9bdd97632cf656c69113f7cd6a361f2a67221cb6"}, + {file = "regex-2024.4.28-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:25f87ae6b96374db20f180eab083aafe419b194e96e4f282c40191e71980c666"}, + {file = "regex-2024.4.28-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:5dbc1bcc7413eebe5f18196e22804a3be1bfdfc7e2afd415e12c068624d48247"}, + {file = "regex-2024.4.28-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f85151ec5a232335f1be022b09fbbe459042ea1951d8a48fef251223fc67eee1"}, + {file = "regex-2024.4.28-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:57ba112e5530530fd175ed550373eb263db4ca98b5f00694d73b18b9a02e7185"}, + {file = "regex-2024.4.28-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:224803b74aab56aa7be313f92a8d9911dcade37e5f167db62a738d0c85fdac4b"}, + {file = "regex-2024.4.28-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0a54a047b607fd2d2d52a05e6ad294602f1e0dec2291152b745870afc47c1397"}, + {file = "regex-2024.4.28-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0a2a512d623f1f2d01d881513af9fc6a7c46e5cfffb7dc50c38ce959f9246c94"}, + {file = "regex-2024.4.28-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:c06bf3f38f0707592898428636cbb75d0a846651b053a1cf748763e3063a6925"}, + {file = "regex-2024.4.28-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:1031a5e7b048ee371ab3653aad3030ecfad6ee9ecdc85f0242c57751a05b0ac4"}, + {file = "regex-2024.4.28-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:d7a353ebfa7154c871a35caca7bfd8f9e18666829a1dc187115b80e35a29393e"}, + {file = "regex-2024.4.28-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:7e76b9cfbf5ced1aca15a0e5b6f229344d9b3123439ffce552b11faab0114a02"}, + {file = "regex-2024.4.28-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:5ce479ecc068bc2a74cb98dd8dba99e070d1b2f4a8371a7dfe631f85db70fe6e"}, + {file = "regex-2024.4.28-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:7d77b6f63f806578c604dca209280e4c54f0fa9a8128bb8d2cc5fb6f99da4150"}, + {file = "regex-2024.4.28-cp38-cp38-win32.whl", hash = "sha256:d84308f097d7a513359757c69707ad339da799e53b7393819ec2ea36bc4beb58"}, + {file = "regex-2024.4.28-cp38-cp38-win_amd64.whl", hash = "sha256:2cc1b87bba1dd1a898e664a31012725e48af826bf3971e786c53e32e02adae6c"}, + {file = "regex-2024.4.28-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:7413167c507a768eafb5424413c5b2f515c606be5bb4ef8c5dee43925aa5718b"}, + {file = "regex-2024.4.28-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:108e2dcf0b53a7c4ab8986842a8edcb8ab2e59919a74ff51c296772e8e74d0ae"}, + {file = "regex-2024.4.28-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:f1c5742c31ba7d72f2dedf7968998730664b45e38827637e0f04a2ac7de2f5f1"}, + {file = "regex-2024.4.28-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ecc6148228c9ae25ce403eade13a0961de1cb016bdb35c6eafd8e7b87ad028b1"}, + {file = "regex-2024.4.28-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b7d893c8cf0e2429b823ef1a1d360a25950ed11f0e2a9df2b5198821832e1947"}, + {file = "regex-2024.4.28-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:4290035b169578ffbbfa50d904d26bec16a94526071ebec3dadbebf67a26b25e"}, + {file = "regex-2024.4.28-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:44a22ae1cfd82e4ffa2066eb3390777dc79468f866f0625261a93e44cdf6482b"}, + {file = "regex-2024.4.28-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:fd24fd140b69f0b0bcc9165c397e9b2e89ecbeda83303abf2a072609f60239e2"}, + {file = "regex-2024.4.28-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:39fb166d2196413bead229cd64a2ffd6ec78ebab83fff7d2701103cf9f4dfd26"}, + {file = "regex-2024.4.28-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:9301cc6db4d83d2c0719f7fcda37229691745168bf6ae849bea2e85fc769175d"}, + {file = "regex-2024.4.28-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:7c3d389e8d76a49923683123730c33e9553063d9041658f23897f0b396b2386f"}, + {file = "regex-2024.4.28-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:99ef6289b62042500d581170d06e17f5353b111a15aa6b25b05b91c6886df8fc"}, + {file = "regex-2024.4.28-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:b91d529b47798c016d4b4c1d06cc826ac40d196da54f0de3c519f5a297c5076a"}, + {file = "regex-2024.4.28-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:43548ad74ea50456e1c68d3c67fff3de64c6edb85bcd511d1136f9b5376fc9d1"}, + {file = "regex-2024.4.28-cp39-cp39-win32.whl", hash = "sha256:05d9b6578a22db7dedb4df81451f360395828b04f4513980b6bd7a1412c679cc"}, + {file = "regex-2024.4.28-cp39-cp39-win_amd64.whl", hash = "sha256:3986217ec830c2109875be740531feb8ddafe0dfa49767cdcd072ed7e8927962"}, + {file = "regex-2024.4.28.tar.gz", hash = "sha256:83ab366777ea45d58f72593adf35d36ca911ea8bd838483c1823b883a121b0e4"}, ] [[package]] @@ -2761,6 +2796,19 @@ files = [ [package.dependencies] mpmath = ">=0.19" +[[package]] +name = "tbb" +version = "2021.12.0" +description = "Intel® oneAPI Threading Building Blocks (oneTBB)" +optional = true +python-versions = "*" +files = [ + {file = "tbb-2021.12.0-py2.py3-none-manylinux1_i686.whl", hash = "sha256:f2cc9a7f8ababaa506cbff796ce97c3bf91062ba521e15054394f773375d81d8"}, + {file = "tbb-2021.12.0-py2.py3-none-manylinux1_x86_64.whl", hash = "sha256:a925e9a7c77d3a46ae31c34b0bb7f801c4118e857d137b68f68a8e458fcf2bd7"}, + {file = "tbb-2021.12.0-py3-none-win32.whl", hash = "sha256:b1725b30c174048edc8be70bd43bb95473f396ce895d91151a474d0fa9f450a8"}, + {file = "tbb-2021.12.0-py3-none-win_amd64.whl", hash = "sha256:fc2772d850229f2f3df85f1109c4844c495a2db7433d38200959ee9265b34789"}, +] + [[package]] name = "texttable" version = "1.7.0" @@ -2902,42 +2950,38 @@ files = [ [[package]] name = "torch" -version = "2.2.2" +version = "2.3.0" description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration" optional = true python-versions = ">=3.8.0" files = [ - {file = "torch-2.2.2-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:bc889d311a855dd2dfd164daf8cc903a6b7273a747189cebafdd89106e4ad585"}, - {file = "torch-2.2.2-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:15dffa4cc3261fa73d02f0ed25f5fa49ecc9e12bf1ae0a4c1e7a88bbfaad9030"}, - {file = "torch-2.2.2-cp310-cp310-win_amd64.whl", hash = "sha256:11e8fe261233aeabd67696d6b993eeb0896faa175c6b41b9a6c9f0334bdad1c5"}, - {file = "torch-2.2.2-cp310-none-macosx_10_9_x86_64.whl", hash = "sha256:b2e2200b245bd9f263a0d41b6a2dab69c4aca635a01b30cca78064b0ef5b109e"}, - {file = "torch-2.2.2-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:877b3e6593b5e00b35bbe111b7057464e76a7dd186a287280d941b564b0563c2"}, - {file = "torch-2.2.2-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:ad4c03b786e074f46606f4151c0a1e3740268bcf29fbd2fdf6666d66341c1dcb"}, - {file = "torch-2.2.2-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:32827fa1fbe5da8851686256b4cd94cc7b11be962862c2293811c94eea9457bf"}, - {file = "torch-2.2.2-cp311-cp311-win_amd64.whl", hash = "sha256:f9ef0a648310435511e76905f9b89612e45ef2c8b023bee294f5e6f7e73a3e7c"}, - {file = "torch-2.2.2-cp311-none-macosx_10_9_x86_64.whl", hash = "sha256:95b9b44f3bcebd8b6cd8d37ec802048c872d9c567ba52c894bba90863a439059"}, - {file = "torch-2.2.2-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:49aa4126ede714c5aeef7ae92969b4b0bbe67f19665106463c39f22e0a1860d1"}, - {file = "torch-2.2.2-cp312-cp312-manylinux1_x86_64.whl", hash = "sha256:cf12cdb66c9c940227ad647bc9cf5dba7e8640772ae10dfe7569a0c1e2a28aca"}, - {file = "torch-2.2.2-cp312-cp312-manylinux2014_aarch64.whl", hash = "sha256:89ddac2a8c1fb6569b90890955de0c34e1724f87431cacff4c1979b5f769203c"}, - {file = "torch-2.2.2-cp312-cp312-win_amd64.whl", hash = "sha256:451331406b760f4b1ab298ddd536486ab3cfb1312614cfe0532133535be60bea"}, - {file = "torch-2.2.2-cp312-none-macosx_10_9_x86_64.whl", hash = "sha256:eb4d6e9d3663e26cd27dc3ad266b34445a16b54908e74725adb241aa56987533"}, - {file = "torch-2.2.2-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:bf9558da7d2bf7463390b3b2a61a6a3dbb0b45b161ee1dd5ec640bf579d479fc"}, - {file = "torch-2.2.2-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:cd2bf7697c9e95fb5d97cc1d525486d8cf11a084c6af1345c2c2c22a6b0029d0"}, - {file = "torch-2.2.2-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:b421448d194496e1114d87a8b8d6506bce949544e513742b097e2ab8f7efef32"}, - {file = "torch-2.2.2-cp38-cp38-win_amd64.whl", hash = "sha256:3dbcd563a9b792161640c0cffe17e3270d85e8f4243b1f1ed19cca43d28d235b"}, - {file = "torch-2.2.2-cp38-none-macosx_10_9_x86_64.whl", hash = "sha256:31f4310210e7dda49f1fb52b0ec9e59382cfcb938693f6d5378f25b43d7c1d29"}, - {file = "torch-2.2.2-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:c795feb7e8ce2e0ef63f75f8e1ab52e7fd5e1a4d7d0c31367ade1e3de35c9e95"}, - {file = "torch-2.2.2-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:a6e5770d68158d07456bfcb5318b173886f579fdfbf747543901ce718ea94782"}, - {file = "torch-2.2.2-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:67dcd726edff108e2cd6c51ff0e416fd260c869904de95750e80051358680d24"}, - {file = "torch-2.2.2-cp39-cp39-win_amd64.whl", hash = "sha256:539d5ef6c4ce15bd3bd47a7b4a6e7c10d49d4d21c0baaa87c7d2ef8698632dfb"}, - {file = "torch-2.2.2-cp39-none-macosx_10_9_x86_64.whl", hash = "sha256:dff696de90d6f6d1e8200e9892861fd4677306d0ef604cb18f2134186f719f82"}, - {file = "torch-2.2.2-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:3a4dd910663fd7a124c056c878a52c2b0be4a5a424188058fe97109d4436ee42"}, + {file = "torch-2.3.0-cp310-cp310-manylinux1_x86_64.whl", hash = "sha256:d8ea5a465dbfd8501f33c937d1f693176c9aef9d1c1b0ca1d44ed7b0a18c52ac"}, + {file = "torch-2.3.0-cp310-cp310-manylinux2014_aarch64.whl", hash = "sha256:09c81c5859a5b819956c6925a405ef1cdda393c9d8a01ce3851453f699d3358c"}, + {file = "torch-2.3.0-cp310-cp310-win_amd64.whl", hash = "sha256:1bf023aa20902586f614f7682fedfa463e773e26c58820b74158a72470259459"}, + {file = "torch-2.3.0-cp310-none-macosx_11_0_arm64.whl", hash = "sha256:758ef938de87a2653bba74b91f703458c15569f1562bf4b6c63c62d9c5a0c1f5"}, + {file = "torch-2.3.0-cp311-cp311-manylinux1_x86_64.whl", hash = "sha256:493d54ee2f9df100b5ce1d18c96dbb8d14908721f76351e908c9d2622773a788"}, + {file = "torch-2.3.0-cp311-cp311-manylinux2014_aarch64.whl", hash = "sha256:bce43af735c3da16cc14c7de2be7ad038e2fbf75654c2e274e575c6c05772ace"}, + {file = "torch-2.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:729804e97b7cf19ae9ab4181f91f5e612af07956f35c8b2c8e9d9f3596a8e877"}, + {file = "torch-2.3.0-cp311-none-macosx_11_0_arm64.whl", hash = "sha256:d24e328226d8e2af7cf80fcb1d2f1d108e0de32777fab4aaa2b37b9765d8be73"}, + {file = "torch-2.3.0-cp312-cp312-manylinux1_x86_64.whl", hash = "sha256:b0de2bdc0486ea7b14fc47ff805172df44e421a7318b7c4d92ef589a75d27410"}, + {file = "torch-2.3.0-cp312-cp312-manylinux2014_aarch64.whl", hash = "sha256:a306c87a3eead1ed47457822c01dfbd459fe2920f2d38cbdf90de18f23f72542"}, + {file = "torch-2.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:f9b98bf1a3c8af2d4c41f0bf1433920900896c446d1ddc128290ff146d1eb4bd"}, + {file = "torch-2.3.0-cp312-none-macosx_11_0_arm64.whl", hash = "sha256:dca986214267b34065a79000cee54232e62b41dff1ec2cab9abc3fc8b3dee0ad"}, + {file = "torch-2.3.0-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:20572f426965dd8a04e92a473d7e445fa579e09943cc0354f3e6fef6130ce061"}, + {file = "torch-2.3.0-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:e65ba85ae292909cde0dde6369826d51165a3fc8823dc1854cd9432d7f79b932"}, + {file = "torch-2.3.0-cp38-cp38-win_amd64.whl", hash = "sha256:5515503a193781fd1b3f5c474e89c9dfa2faaa782b2795cc4a7ab7e67de923f6"}, + {file = "torch-2.3.0-cp38-none-macosx_11_0_arm64.whl", hash = "sha256:6ae9f64b09516baa4ef890af0672dc981c20b1f0d829ce115d4420a247e88fba"}, + {file = "torch-2.3.0-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:cd0dc498b961ab19cb3f8dbf0c6c50e244f2f37dbfa05754ab44ea057c944ef9"}, + {file = "torch-2.3.0-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:e05f836559251e4096f3786ee99f4a8cbe67bc7fbedba8ad5e799681e47c5e80"}, + {file = "torch-2.3.0-cp39-cp39-win_amd64.whl", hash = "sha256:4fb27b35dbb32303c2927da86e27b54a92209ddfb7234afb1949ea2b3effffea"}, + {file = "torch-2.3.0-cp39-none-macosx_11_0_arm64.whl", hash = "sha256:760f8bedff506ce9e6e103498f9b1e9e15809e008368594c3a66bf74a8a51380"}, ] [package.dependencies] filelock = "*" fsspec = "*" jinja2 = "*" +mkl = {version = ">=2021.1.1,<=2021.4.0", markers = "platform_system == \"Windows\""} networkx = "*" nvidia-cublas-cu12 = {version = "12.1.3.1", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} nvidia-cuda-cupti-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} @@ -2948,10 +2992,10 @@ nvidia-cufft-cu12 = {version = "11.0.2.54", markers = "platform_system == \"Linu nvidia-curand-cu12 = {version = "10.3.2.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} nvidia-cusolver-cu12 = {version = "11.4.5.107", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} nvidia-cusparse-cu12 = {version = "12.1.0.106", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} -nvidia-nccl-cu12 = {version = "2.19.3", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} +nvidia-nccl-cu12 = {version = "2.20.5", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} nvidia-nvtx-cu12 = {version = "12.1.105", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\""} sympy = "*" -triton = {version = "2.2.0", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version < \"3.12\""} +triton = {version = "2.3.0", markers = "platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version < \"3.12\""} typing-extensions = ">=4.8.0" [package.extras] @@ -2980,13 +3024,13 @@ telegram = ["requests"] [[package]] name = "transformers" -version = "4.40.0" +version = "4.40.1" description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow" optional = false python-versions = ">=3.8.0" files = [ - {file = "transformers-4.40.0-py3-none-any.whl", hash = "sha256:92797ec3368ed4476a053529a4039a12ad09167d9e371981dda4afb4bdf590ac"}, - {file = "transformers-4.40.0.tar.gz", hash = "sha256:fdb01dfe6a492bd34e3fa2aefffa470b1d8a2341db47a932f83ed33839d96b03"}, + {file = "transformers-4.40.1-py3-none-any.whl", hash = "sha256:9d5ee0c8142a60501faf9e49a0b42f8e9cb8611823bce4f195a9325a6816337e"}, + {file = "transformers-4.40.1.tar.gz", hash = "sha256:55e1697e6f18b58273e7117bb469cdffc11be28995462d8d5e422fef38d2de36"}, ] [package.dependencies] @@ -3048,17 +3092,17 @@ vision = ["Pillow (>=10.0.1,<=15.0)"] [[package]] name = "triton" -version = "2.2.0" +version = "2.3.0" description = "A language and compiler for custom Deep Learning operations" optional = true python-versions = "*" files = [ - {file = "triton-2.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a2294514340cfe4e8f4f9e5c66c702744c4a117d25e618bd08469d0bfed1e2e5"}, - {file = "triton-2.2.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:da58a152bddb62cafa9a857dd2bc1f886dbf9f9c90a2b5da82157cd2b34392b0"}, - {file = "triton-2.2.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0af58716e721460a61886668b205963dc4d1e4ac20508cc3f623aef0d70283d5"}, - {file = "triton-2.2.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e8fe46d3ab94a8103e291bd44c741cc294b91d1d81c1a2888254cbf7ff846dab"}, - {file = "triton-2.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b8ce26093e539d727e7cf6f6f0d932b1ab0574dc02567e684377630d86723ace"}, - {file = "triton-2.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:227cc6f357c5efcb357f3867ac2a8e7ecea2298cd4606a8ba1e931d1d5a947df"}, + {file = "triton-2.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5ce4b8ff70c48e47274c66f269cce8861cf1dc347ceeb7a67414ca151b1822d8"}, + {file = "triton-2.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3c3d9607f85103afdb279938fc1dd2a66e4f5999a58eb48a346bd42738f986dd"}, + {file = "triton-2.3.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:218d742e67480d9581bafb73ed598416cc8a56f6316152e5562ee65e33de01c0"}, + {file = "triton-2.3.0-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:381ec6b3dac06922d3e4099cfc943ef032893b25415de295e82b1a82b0359d2c"}, + {file = "triton-2.3.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:038e06a09c06a164fef9c48de3af1e13a63dc1ba3c792871e61a8e79720ea440"}, + {file = "triton-2.3.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6d8f636e0341ac348899a47a057c3daea99ea7db31528a225a3ba4ded28ccc65"}, ] [package.dependencies] @@ -3452,4 +3496,4 @@ torch = ["torch"] [metadata] lock-version = "2.0" python-versions = ">=3.9,<3.13" -content-hash = "438514f5cf9978fbd39b910596634e6ec4a6191d10026dafbb026808eb63c70b" +content-hash = "df83b265d0263870b5d1ae8bfd847f406abef90868fdf528ff38527b512f86c0" diff --git a/server/pyproject.toml b/server/pyproject.toml index 23dc5eee..3868c962 100644 --- a/server/pyproject.toml +++ b/server/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "text-generation-server" -version = "2.0.1" +version = "2.0.2" description = "Text Generation Inference Python gRPC Server" authors = ["Olivier Dehaene "] @@ -31,10 +31,12 @@ einops = "^0.6.1" texttable = { version = "^1.6.7", optional = true } datasets = { version = "^2.14.0", optional = true } peft = { version = "^0.10", optional = true } -torch = { version = "^2.1.1", optional = true } +torch = { version = "^2.3.0", optional = true } scipy = "^1.11.1" pillow = "^10.0.0" outlines= { version = "^0.0.36", optional = true } +prometheus-client = "^0.20.0" +py-cpuinfo = "^9.0.0" [tool.poetry.extras] torch = ["torch"] diff --git a/server/requirements_cuda.txt b/server/requirements_cuda.txt index 5cd03130..c2714764 100644 --- a/server/requirements_cuda.txt +++ b/server/requirements_cuda.txt @@ -5,13 +5,13 @@ click==8.1.7 ; python_version >= "3.9" and python_version < "3.13" colorama==0.4.6 ; python_version >= "3.9" and python_version < "3.13" and (sys_platform == "win32" or platform_system == "Windows") deprecated==1.2.14 ; python_version >= "3.9" and python_version < "3.13" einops==0.6.1 ; python_version >= "3.9" and python_version < "3.13" -filelock==3.13.4 ; python_version >= "3.9" and python_version < "3.13" -fsspec==2024.2.0 ; python_version >= "3.9" and python_version < "3.13" +filelock==3.14.0 ; python_version >= "3.9" and python_version < "3.13" +fsspec==2024.3.1 ; python_version >= "3.9" and python_version < "3.13" googleapis-common-protos==1.63.0 ; python_version >= "3.9" and python_version < "3.13" grpc-interceptor==0.15.4 ; python_version >= "3.9" and python_version < "3.13" -grpcio-reflection==1.62.1 ; python_version >= "3.9" and python_version < "3.13" -grpcio-status==1.62.1 ; python_version >= "3.9" and python_version < "3.13" -grpcio==1.62.1 ; python_version >= "3.9" and python_version < "3.13" +grpcio-reflection==1.62.2 ; python_version >= "3.9" and python_version < "3.13" +grpcio-status==1.62.2 ; python_version >= "3.9" and python_version < "3.13" +grpcio==1.62.2 ; python_version >= "3.9" and python_version < "3.13" hf-transfer==0.1.6 ; python_version >= "3.9" and python_version < "3.13" huggingface-hub==0.19.4 ; python_version >= "3.9" and python_version < "3.13" idna==3.7 ; python_version >= "3.9" and python_version < "3.13" @@ -28,9 +28,11 @@ opentelemetry-sdk==1.15.0 ; python_version >= "3.9" and python_version < "3.13" opentelemetry-semantic-conventions==0.36b0 ; python_version >= "3.9" and python_version < "3.13" packaging==24.0 ; python_version >= "3.9" and python_version < "3.13" pillow==10.3.0 ; python_version >= "3.9" and python_version < "3.13" +prometheus-client==0.20.0 ; python_version >= "3.9" and python_version < "3.13" protobuf==4.25.3 ; python_version >= "3.9" and python_version < "3.13" +py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13" pyyaml==6.0.1 ; python_version >= "3.9" and python_version < "3.13" -regex==2024.4.16 ; python_version >= "3.9" and python_version < "3.13" +regex==2024.4.28 ; python_version >= "3.9" and python_version < "3.13" requests==2.31.0 ; python_version >= "3.9" and python_version < "3.13" safetensors==0.4.3 ; python_version >= "3.9" and python_version < "3.13" scipy==1.13.0 ; python_version >= "3.9" and python_version < "3.13" @@ -38,7 +40,7 @@ sentencepiece==0.1.99 ; python_version >= "3.9" and python_version < "3.13" setuptools==69.5.1 ; python_version >= "3.9" and python_version < "3.13" tokenizers==0.19.1 ; python_version >= "3.9" and python_version < "3.13" tqdm==4.66.2 ; python_version >= "3.9" and python_version < "3.13" -transformers==4.40.0 ; python_version >= "3.9" and python_version < "3.13" +transformers==4.40.1 ; python_version >= "3.9" and python_version < "3.13" typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13" typing-extensions==4.11.0 ; python_version >= "3.9" and python_version < "3.13" urllib3==2.2.1 ; python_version >= "3.9" and python_version < "3.13" diff --git a/server/requirements_rocm.txt b/server/requirements_rocm.txt index 5cd03130..c2714764 100644 --- a/server/requirements_rocm.txt +++ b/server/requirements_rocm.txt @@ -5,13 +5,13 @@ click==8.1.7 ; python_version >= "3.9" and python_version < "3.13" colorama==0.4.6 ; python_version >= "3.9" and python_version < "3.13" and (sys_platform == "win32" or platform_system == "Windows") deprecated==1.2.14 ; python_version >= "3.9" and python_version < "3.13" einops==0.6.1 ; python_version >= "3.9" and python_version < "3.13" -filelock==3.13.4 ; python_version >= "3.9" and python_version < "3.13" -fsspec==2024.2.0 ; python_version >= "3.9" and python_version < "3.13" +filelock==3.14.0 ; python_version >= "3.9" and python_version < "3.13" +fsspec==2024.3.1 ; python_version >= "3.9" and python_version < "3.13" googleapis-common-protos==1.63.0 ; python_version >= "3.9" and python_version < "3.13" grpc-interceptor==0.15.4 ; python_version >= "3.9" and python_version < "3.13" -grpcio-reflection==1.62.1 ; python_version >= "3.9" and python_version < "3.13" -grpcio-status==1.62.1 ; python_version >= "3.9" and python_version < "3.13" -grpcio==1.62.1 ; python_version >= "3.9" and python_version < "3.13" +grpcio-reflection==1.62.2 ; python_version >= "3.9" and python_version < "3.13" +grpcio-status==1.62.2 ; python_version >= "3.9" and python_version < "3.13" +grpcio==1.62.2 ; python_version >= "3.9" and python_version < "3.13" hf-transfer==0.1.6 ; python_version >= "3.9" and python_version < "3.13" huggingface-hub==0.19.4 ; python_version >= "3.9" and python_version < "3.13" idna==3.7 ; python_version >= "3.9" and python_version < "3.13" @@ -28,9 +28,11 @@ opentelemetry-sdk==1.15.0 ; python_version >= "3.9" and python_version < "3.13" opentelemetry-semantic-conventions==0.36b0 ; python_version >= "3.9" and python_version < "3.13" packaging==24.0 ; python_version >= "3.9" and python_version < "3.13" pillow==10.3.0 ; python_version >= "3.9" and python_version < "3.13" +prometheus-client==0.20.0 ; python_version >= "3.9" and python_version < "3.13" protobuf==4.25.3 ; python_version >= "3.9" and python_version < "3.13" +py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13" pyyaml==6.0.1 ; python_version >= "3.9" and python_version < "3.13" -regex==2024.4.16 ; python_version >= "3.9" and python_version < "3.13" +regex==2024.4.28 ; python_version >= "3.9" and python_version < "3.13" requests==2.31.0 ; python_version >= "3.9" and python_version < "3.13" safetensors==0.4.3 ; python_version >= "3.9" and python_version < "3.13" scipy==1.13.0 ; python_version >= "3.9" and python_version < "3.13" @@ -38,7 +40,7 @@ sentencepiece==0.1.99 ; python_version >= "3.9" and python_version < "3.13" setuptools==69.5.1 ; python_version >= "3.9" and python_version < "3.13" tokenizers==0.19.1 ; python_version >= "3.9" and python_version < "3.13" tqdm==4.66.2 ; python_version >= "3.9" and python_version < "3.13" -transformers==4.40.0 ; python_version >= "3.9" and python_version < "3.13" +transformers==4.40.1 ; python_version >= "3.9" and python_version < "3.13" typer==0.6.1 ; python_version >= "3.9" and python_version < "3.13" typing-extensions==4.11.0 ; python_version >= "3.9" and python_version < "3.13" urllib3==2.2.1 ; python_version >= "3.9" and python_version < "3.13" From 6073ece4fc2d7180c2057cb49b9ea436463fd52b Mon Sep 17 00:00:00 2001 From: drbh Date: Wed, 1 May 2024 03:03:25 -0400 Subject: [PATCH 20/22] fix: split docs and start conceptual page (#1836) This PR improves the guidance docs and adds a section that explains how grammars are applied on a technical level --- docs/source/_toctree.yml | 4 +- docs/source/basic_tutorials/using_guidance.md | 419 ++++++++++++++++ docs/source/conceptual/guidance.md | 459 +++--------------- 3 files changed, 482 insertions(+), 400 deletions(-) create mode 100644 docs/source/basic_tutorials/using_guidance.md diff --git a/docs/source/_toctree.yml b/docs/source/_toctree.yml index 79a2102f..c815b535 100644 --- a/docs/source/_toctree.yml +++ b/docs/source/_toctree.yml @@ -25,6 +25,8 @@ title: Non-core Model Serving - local: basic_tutorials/safety title: Safety + - local: basic_tutorials/using_guidance + title: Using Guidance, JSON, tools - local: basic_tutorials/visual_language_models title: Visual Language Models title: Tutorials @@ -44,6 +46,6 @@ - local: conceptual/speculation title: Speculation (Medusa, ngram) - local: conceptual/guidance - title: Guidance, JSON, tools (using outlines) + title: How Guidance Works (via outlines) title: Conceptual Guides diff --git a/docs/source/basic_tutorials/using_guidance.md b/docs/source/basic_tutorials/using_guidance.md new file mode 100644 index 00000000..606f2453 --- /dev/null +++ b/docs/source/basic_tutorials/using_guidance.md @@ -0,0 +1,419 @@ +# Guidance + +Text Generation Inference (TGI) now supports [JSON and regex grammars](#grammar-and-constraints) and [tools and functions](#tools-and-functions) to help developers guide LLM responses to fit their needs. + +These feature are available starting from version `1.4.3`. They are accessible via the [text_generation](https://pypi.org/project/text-generation/) library. The tool support is compatible with OpenAI's client libraries. The following guide will walk you through the new features and how to use them! + +_note: guidance is supported as grammar in the `/generate` endpoint and as tools in the `/chat/completions` endpoint._ + +## How it works + +TGI leverages the [outlines](https://github.com/outlines-dev/outlines) library to efficiently parse and compile the grammatical structures and tools specified by users. This integration transforms the defined grammars into an intermediate representation that acts as a framework to guide and constrain content generation, ensuring that outputs adhere to the specified grammatical rules. + +If you are interested in the technical details on how outlines is used in TGI, you can check out the [conceptual guidance documentation](../conceptual/guidance). + +## Table of Contents 📚 + +### Grammar and Constraints + +- [The Grammar Parameter](#the-grammar-parameter): Shape your AI's responses with precision. +- [Constrain with Pydantic](#constrain-with-pydantic): Define a grammar using Pydantic models. +- [JSON Schema Integration](#json-schema-integration): Fine-grained control over your requests via JSON schema. +- [Using the client](#using-the-client): Use TGI's client libraries to shape the AI's responses. + +### Tools and Functions + +- [The Tools Parameter](#the-tools-parameter): Enhance the AI's capabilities with predefined functions. +- [Via the client](#text-generation-inference-client): Use TGI's client libraries to interact with the Messages API and Tool functions. +- [OpenAI integration](#openai-integration): Use OpenAI's client libraries to interact with TGI's Messages API and Tool functions. + +## Grammar and Constraints 🛣️ + +### The Grammar Parameter + +In TGI `1.4.3`, we've introduced the grammar parameter, which allows you to specify the format of the response you want from the LLM. + +Using curl, you can make a request to TGI's Messages API with the grammar parameter. This is the most primitive way to interact with the API and using [Pydantic](#constrain-with-pydantic) is recommended for ease of use and readability. + +```json +curl localhost:3000/generate \ + -X POST \ + -H 'Content-Type: application/json' \ + -d '{ + "inputs": "I saw a puppy a cat and a raccoon during my bike ride in the park", + "parameters": { + "repetition_penalty": 1.3, + "grammar": { + "type": "json", + "value": { + "properties": { + "location": { + "type": "string" + }, + "activity": { + "type": "string" + }, + "animals_seen": { + "type": "integer", + "minimum": 1, + "maximum": 5 + }, + "animals": { + "type": "array", + "items": { + "type": "string" + } + } + }, + "required": ["location", "activity", "animals_seen", "animals"] + } + } + } +}' +// {"generated_text":"{ \n\n\"activity\": \"biking\",\n\"animals\": [\"puppy\",\"cat\",\"raccoon\"],\n\"animals_seen\": 3,\n\"location\": \"park\"\n}"} + +``` + +A grammar can be defined using Pydantic models, JSON schemas, or regular expressions. The LLM will then generate a response that conforms to the specified grammar. + +> Note: A grammar must compile to an intermediate representation to constrain the output. Grammar compilation is a computationally expensive and may take a few seconds to complete on the first request. Subsequent requests will use the cached grammar and will be much faster. + +### Constrain with Pydantic + +Using Pydantic models we can define a similar grammar as the previous example in a shorter and more readable way. + +```python +import requests +from pydantic import BaseModel, conint +from typing import List + +class Animals(BaseModel): + location: str + activity: str + animals_seen: conint(ge=1, le=5) # Constrained integer type + animals: List[str] + +prompt = "convert to JSON: I saw a puppy a cat and a raccoon during my bike ride in the park" + +data = { + "inputs": prompt, + "parameters": { + "repetition_penalty": 1.3, + "grammar": { + "type": "json", + "value": Animals.schema() + } + } +} + +headers = { + "Content-Type": "application/json", +} + +response = requests.post( + 'http://127.0.0.1:3000/generate', + headers=headers, + json=data +) +print(response.json()) +# {'generated_text': '{ "activity": "bike riding", "animals": ["puppy","cat","raccoon"],"animals_seen": 3, "location":"park" }'} + +``` + +### JSON Schema Integration + +If Pydantic's not your style, go raw with direct JSON Schema integration. This is similar to the first example but with programmatic control. + +```python +import requests + +json_schema = { + "properties": { + "location": { + "type": "string" + }, + "activity": { + "type": "string" + }, + "animals_seen": { + "type": "integer", + "minimum": 1, + "maximum": 5 + }, + "animals": { + "type": "array", + "items": { + "type": "string" + } + } + }, + "required": ["location", "activity", "animals_seen", "animals"] +} + +data = { + "inputs": "convert to JSON: I saw a puppy a cat and a raccoon during my bike ride in the park", + "parameters": { + "max_new_tokens": 200, + "repetition_penalty": 1.3, + "grammar": { + "type": "json", + "value": json_schema + } + } +} + +headers = { + "Content-Type": "application/json", +} + +response = requests.post( + 'http://127.0.0.1:3000/generate', + headers=headers, + json=data +) +print(response.json()) +# {'generated_text': '{\n"activity": "biking",\n"animals": ["puppy","cat","raccoon"]\n , "animals_seen": 3,\n "location":"park"}'} + +``` + +### Using the client + +TGI provides a client library to that make it easy to send requests with all of the parameters we've discussed above. Here's an example of how to use the client to send a request with a grammar parameter. + +```python +from text_generation import AsyncClient +from text_generation.types import GrammarType + +# NOTE: tools defined above and removed for brevity + +# Define an async function to encapsulate the async operation +async def main(): + client = AsyncClient(base_url="http://localhost:3000") + + # Use 'await' to wait for the async method 'chat' to complete + response = await client.generate( + "Whats Googles DNS", + max_new_tokens=10, + decoder_input_details=True, + seed=1, + grammar={ + "type": GrammarType.Regex, + "value": "((25[0-5]|2[0-4]\\d|[01]?\\d\\d?)\\.){3}(25[0-5]|2[0-4]\\d|[01]?\\d\\d?)", + }, + ) + + # Once the response is received, you can process it + print(response.generated_text) + +# Ensure the main async function is run in the event loop +if __name__ == "__main__": + import asyncio + asyncio.run(main()) + +# 118.8.0.84 + +``` + +## Tools and Functions 🛠️ + +### The Tools Parameter + +In addition to the grammar parameter, we've also introduced a set of tools and functions to help you get the most out of the Messages API. + +Tools are a set of user defined functions that can be used in tandem with the chat functionality to enhance the LLM's capabilities. Functions, similar to grammar are defined as JSON schema and can be passed as part of the parameters to the Messages API. + +Functions, similar to grammar are defined as JSON schema and can be passed as part of the parameters to the Messages API. + +```json +curl localhost:3000/v1/chat/completions \ + -X POST \ + -H 'Content-Type: application/json' \ + -d '{ + "model": "tgi", + "messages": [ + { + "role": "user", + "content": "What is the weather like in New York?" + } + ], + "tools": [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "format": { + "type": "string", + "enum": ["celsius", "fahrenheit"], + "description": "The temperature unit to use. Infer this from the users location." + } + }, + "required": ["location", "format"] + } + } + } + ], + "tool_choice": "get_current_weather" +}' +// {"id":"","object":"text_completion","created":1709051640,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-native","choices":[{"index":0,"message":{"role":"assistant","tool_calls":{"id":0,"type":"function","function":{"description":null,"name":"tools","parameters":{"format":"celsius","location":"New York"}}}},"logprobs":null,"finish_reason":"eos_token"}],"usage":{"prompt_tokens":157,"completion_tokens":19,"total_tokens":176}} +``` + +### Text Generation Inference Client + +TGI provides a client library to interact with the Messages API and Tool functions. The client library is available in both synchronous and asynchronous versions. + +```python +from text_generation import AsyncClient + +# NOTE: tools defined above and removed for brevity + +# Define an async function to encapsulate the async operation +async def main(): + client = AsyncClient(base_url="http://localhost:3000") + + # Use 'await' to wait for the async method 'chat' to complete + response = await client.chat( + max_tokens=100, + seed=1, + tools=tools, + presence_penalty=-1.1, + messages=[ + { + "role": "system", + "content": "You're a helpful assistant! Answer the users question best you can.", + }, + { + "role": "user", + "content": "What is the weather like in Brooklyn, New York?", + }, + ], + ) + + # Once the response is received, you can process it + print(response.choices[0].message.tool_calls) + +# Ensure the main async function is run in the event loop +if __name__ == "__main__": + import asyncio + asyncio.run(main()) + +# {"id":"","object":"text_completion","created":1709051942,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-native","choices":[{"index":0,"message":{"role":"assistant","tool_calls":{"id":0,"type":"function","function":{"description":null,"name":"tools","parameters":{"format":"celsius","location":"New York"}}}},"logprobs":null,"finish_reason":"eos_token"}],"usage":{"prompt_tokens":157,"completion_tokens":20,"total_tokens":177}} + +``` + +
+ Tools used in example above + +```python + tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "format": { + "type": "string", + "enum": ["celsius", "fahrenheit"], + "description": "The temperature unit to use. Infer this from the users location.", + }, + }, + "required": ["location", "format"], + }, + }, + }, + { + "type": "function", + "function": { + "name": "get_n_day_weather_forecast", + "description": "Get an N-day weather forecast", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "format": { + "type": "string", + "enum": ["celsius", "fahrenheit"], + "description": "The temperature unit to use. Infer this from the users location.", + }, + "num_days": { + "type": "integer", + "description": "The number of days to forecast", + }, + }, + "required": ["location", "format", "num_days"], + }, + }, + } + ] +``` + +
+ +### OpenAI integration + +TGI exposes an OpenAI-compatible API, which means you can use OpenAI's client libraries to interact with TGI's Messages API and Tool functions. + +However there are some minor differences in the API, for example `tool_choice="auto"` will ALWAYS choose the tool for you. This is different from OpenAI's API where `tool_choice="auto"` will choose a tool if the model thinks it's necessary. + +```python +from openai import OpenAI + +# Initialize the client, pointing it to one of the available models +client = OpenAI( + base_url="http://localhost:3000/v1", + api_key="_", +) + +# NOTE: tools defined above and removed for brevity + +chat_completion = client.chat.completions.create( + model="tgi", + messages=[ + { + "role": "system", + "content": "Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.", + }, + { + "role": "user", + "content": "What's the weather like the next 3 days in San Francisco, CA?", + }, + ], + tools=tools, + tool_choice="auto", # tool selected by model + max_tokens=500, +) + + +called = chat_completion.choices[0].message.tool_calls +print(called) +# { +# "id": 0, +# "type": "function", +# "function": { +# "description": None, +# "name": "tools", +# "parameters": { +# "format": "celsius", +# "location": "San Francisco, CA", +# "num_days": 3, +# }, +# }, +# } +``` diff --git a/docs/source/conceptual/guidance.md b/docs/source/conceptual/guidance.md index d3ec5fb9..0ce34f2f 100644 --- a/docs/source/conceptual/guidance.md +++ b/docs/source/conceptual/guidance.md @@ -1,425 +1,86 @@ # Guidance -Text Generation Inference (TGI) now supports [JSON and regex grammars](#grammar-and-constraints) and [tools and functions](#tools-and-functions) to help developers guide LLM responses to fit their needs. +## What is Guidance? -These feature are available starting from version `1.4.3`. They are accessible via the [text_generation](https://pypi.org/project/text-generation/) library. The tool support is compatible with OpenAI's client libraries. The following guide will walk you through the new features and how to use them! +Guidance is a feature that allows users to constrain the generation of a large language model with a specified grammar. This feature is particularly useful when you want to generate text that follows a specific structure or uses a specific set of words or produce output in a specific format. -> The Grammar guidance support is currently only available in the TGI API due to lack of support in Open AI API. +## How is it used? -## Quick Start +Guidance can be in many ways and the community is always finding new ways to use it. Here are some examples of how you can use guidance: -Before we jump into the deep end, ensure your system is using TGI version `1.4.3` or later to access all the features we're about to explore in this guide. +Technically, guidance can be used to generate: -If you're not up to date, grab the latest version and let's get started! +- a specific JSON object +- a function signature +- typed output like a list of integers -## How it works +However these use cases can span a wide range of applications, such as: -TGI leverages the [outlines](https://github.com/outlines-dev/outlines) library to efficiently parse and compile the grammatical structures and tools specified by users. This integration transforms the defined grammars into an intermediate representation that acts as a framework to guide and constrain content generation, ensuring that outputs adhere to the specified grammatical rules. +- extracting structured data from unstructured text +- summarizing text into a specific format +- limit output to specific classes of words (act as a LLM powered classifier) +- generate the input to specific APIs or services +- provide reliable and consistent output for downstream tasks +- extract data from multimodal inputs -## Table of Contents 📚 +## How it works? -### Grammar and Constraints +Diving into the details, guidance is enabled by including a grammar with a generation request that is compiled, and used to modify the chosen tokens. -- [The Grammar Parameter](#the-grammar-parameter): Shape your AI's responses with precision. -- [Constrain with Pydantic](#constrain-with-pydantic): Define a grammar using Pydantic models. -- [JSON Schema Integration](#json-schema-integration): Fine-grained control over your requests via JSON schema. -- [Using the client](#using-the-client): Use TGI's client libraries to shape the AI's responses. +This process can be broken down into the following steps: -### Tools and Functions +1. A request is sent to the backend, it is processed and placed in batch. Processing includes compiling the grammar into a finite state machine and a grammar state. -- [The Tools Parameter](#the-tools-parameter): Enhance the AI's capabilities with predefined functions. -- [Via the client](#text-generation-inference-client): Use TGI's client libraries to interact with the Messages API and Tool functions. -- [OpenAI integration](#openai-integration): Use OpenAI's client libraries to interact with TGI's Messages API and Tool functions. +
+ + +
-## Grammar and Constraints 🛣️ +2. The model does a forward pass over the batch. This returns probabilities for each token in the vocabulary for each request in the batch. -### The Grammar Parameter +3. The process of choosing one of those tokens is called `sampling`. The model samples from the distribution of probabilities to choose the next token. In TGI all of the steps before sampling are called `processor`. Grammars are applied as a processor that masks out tokens that are not allowed by the grammar. -In TGI `1.4.3`, we've introduced the grammar parameter, which allows you to specify the format of the response you want from the AI. This is a game-changer for those who need precise control over the AI's output. +
+ + +
-Using curl, you can make a request to TGI's Messages API with the grammar parameter. This is the most primitive way to interact with the API and using [Pydantic](#constrain-with-pydantic) is recommended for ease of use and readability. +4. The grammar mask is applied and the model samples from the remaining tokens. Once a token is chosen, we update the grammar state with the new token, to prepare it for the next pass. -```json -curl localhost:3000/generate \ - -X POST \ - -H 'Content-Type: application/json' \ - -d '{ - "inputs": "I saw a puppy a cat and a raccoon during my bike ride in the park", - "parameters": { - "repetition_penalty": 1.3, - "grammar": { - "type": "json", - "value": { - "properties": { - "location": { - "type": "string" - }, - "activity": { - "type": "string" - }, - "animals_seen": { - "type": "integer", - "minimum": 1, - "maximum": 5 - }, - "animals": { - "type": "array", - "items": { - "type": "string" - } - } - }, - "required": ["location", "activity", "animals_seen", "animals"] - } - } - } -}' -// {"generated_text":"{ \n\n\"activity\": \"biking\",\n\"animals\": [\"puppy\",\"cat\",\"raccoon\"],\n\"animals_seen\": 3,\n\"location\": \"park\"\n}"} +
+ + +
-``` +## How to use Guidance? -A grammar can be defined using Pydantic models, JSON schemas, or regular expressions. The AI will then generate a response that conforms to the specified grammar. +There are two main ways to use guidance; you can either use the `/generate` endpoint with a grammar or use the `/chat/completion` endpoint with tools. -> Note: A grammar must compile to an intermediate representation to constrain the output. Grammar compilation is a computationally expensive and may take a few seconds to complete on the first request. Subsequent requests will use the cached grammar and will be much faster. +Under the hood tools are a special case of grammars that allows the model to choose one or none of the provided tools. -### Constrain with Pydantic +Please refer to [using guidance](../basic_tutorial/using_guidance) for more examples and details on how to use guidance in Python, JavaScript, and cURL. -Pydantic is a powerful library for data validation and settings management. It's the perfect tool for crafting the a specific response format. +### Getting the most out of guidance -Using Pydantic models we can define a similar grammar as the previous example in a shorter and more readable way. +Depending on how you are using guidance, you may want to make use of different features. Here are some tips to get the most out of guidance: -```python -import requests -from pydantic import BaseModel, conint -from typing import List - -class Animals(BaseModel): - location: str - activity: str - animals_seen: conint(ge=1, le=5) # Constrained integer type - animals: List[str] - -prompt = "convert to JSON: I saw a puppy a cat and a raccoon during my bike ride in the park" - -data = { - "inputs": prompt, - "parameters": { - "repetition_penalty": 1.3, - "grammar": { - "type": "json", - "value": Animals.schema() - } - } -} - -headers = { - "Content-Type": "application/json", -} - -response = requests.post( - 'http://127.0.0.1:3000/generate', - headers=headers, - json=data -) -print(response.json()) -# {'generated_text': '{ "activity": "bike riding", "animals": ["puppy","cat","raccoon"],"animals_seen": 3, "location":"park" }'} - -``` - -### JSON Schema Integration - -If Pydantic's not your style, go raw with direct JSON Schema integration. It's like having a conversation with the AI in its own language. This is simliar to the first example but with programmatic control. - -```python -import requests - -json_schema = { - "properties": { - "location": { - "type": "string" - }, - "activity": { - "type": "string" - }, - "animals_seen": { - "type": "integer", - "minimum": 1, - "maximum": 5 - }, - "animals": { - "type": "array", - "items": { - "type": "string" - } - } - }, - "required": ["location", "activity", "animals_seen", "animals"] -} - -data = { - "inputs": "convert to JSON: I saw a puppy a cat and a raccoon during my bike ride in the park", - "parameters": { - "max_new_tokens": 200, - "repetition_penalty": 1.3, - "grammar": { - "type": "json", - "value": json_schema - } - } -} - -headers = { - "Content-Type": "application/json", -} - -response = requests.post( - 'http://127.0.0.1:3000/generate', - headers=headers, - json=data -) -print(response.json()) -# {'generated_text': '{\n"activity": "biking",\n"animals": ["puppy","cat","raccoon"]\n , "animals_seen": 3,\n "location":"park"}'} - -``` - -### Using the client - -TGI provides a client library to that make it easy to send requests with all of the parameters we've discussed above. Here's an example of how to use the client to send a request with a grammar parameter. - -```python -from text_generation import AsyncClient -from text_generation.types import GrammarType - -# NOTE: tools defined above and removed for brevity - -# Define an async function to encapsulate the async operation -async def main(): - client = AsyncClient(base_url="http://localhost:3000") - - # Use 'await' to wait for the async method 'chat' to complete - response = await client.generate( - "Whats Googles DNS", - max_new_tokens=10, - decoder_input_details=True, - seed=1, - grammar={ - "type": GrammarType.Regex, - "value": "((25[0-5]|2[0-4]\\d|[01]?\\d\\d?)\\.){3}(25[0-5]|2[0-4]\\d|[01]?\\d\\d?)", - }, - ) - - # Once the response is received, you can process it - print(response.generated_text) - -# Ensure the main async function is run in the event loop -if __name__ == "__main__": - import asyncio - asyncio.run(main()) - -# 118.8.0.84 - -``` - -## Tools and Functions 🛠️ - -### The Tools Parameter - -In addition to the grammar parameter, we've also introduced a set of tools and functions to help you get the most out of the Messages API. - -Tools are a set of user defined functions that can be used in tandem with the chat functionality to enhance the AI's capabilities. You can use these tools to perform a variety of tasks, such as data manipulation, formatting, and more. - -Functions, similar to grammar are defined as JSON schema and can be passed as part of the parameters to the Messages API. - -```json -curl localhost:3000/v1/chat/completions \ - -X POST \ - -H 'Content-Type: application/json' \ - -d '{ - "model": "tgi", - "messages": [ - { - "role": "user", - "content": "What is the weather like in New York?" - } - ], - "tools": [ - { - "type": "function", - "function": { - "name": "get_current_weather", - "description": "Get the current weather", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and state, e.g. San Francisco, CA" - }, - "format": { - "type": "string", - "enum": ["celsius", "fahrenheit"], - "description": "The temperature unit to use. Infer this from the users location." - } - }, - "required": ["location", "format"] - } - } - } - ], - "tool_choice": "get_current_weather" -}' -// {"id":"","object":"text_completion","created":1709051640,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-native","choices":[{"index":0,"message":{"role":"assistant","tool_calls":{"id":0,"type":"function","function":{"description":null,"name":"tools","parameters":{"format":"celsius","location":"New York"}}}},"logprobs":null,"finish_reason":"eos_token"}],"usage":{"prompt_tokens":157,"completion_tokens":19,"total_tokens":176}} -``` - -
- Tools used in example below - -```python - tools = [ - { - "type": "function", - "function": { - "name": "get_current_weather", - "description": "Get the current weather", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and state, e.g. San Francisco, CA", - }, - "format": { - "type": "string", - "enum": ["celsius", "fahrenheit"], - "description": "The temperature unit to use. Infer this from the users location.", - }, - }, - "required": ["location", "format"], - }, - }, - }, - { - "type": "function", - "function": { - "name": "get_n_day_weather_forecast", - "description": "Get an N-day weather forecast", - "parameters": { - "type": "object", - "properties": { - "location": { - "type": "string", - "description": "The city and state, e.g. San Francisco, CA", - }, - "format": { - "type": "string", - "enum": ["celsius", "fahrenheit"], - "description": "The temperature unit to use. Infer this from the users location.", - }, - "num_days": { - "type": "integer", - "description": "The number of days to forecast", - }, - }, - "required": ["location", "format", "num_days"], - }, - }, - } - ] -``` - -
- -### Text Generation Inference Client - -TGI provides a client library to interact with the Messages API and Tool functions. The client library is available in both synchronous and asynchronous versions. - -```python -from text_generation import AsyncClient - -# NOTE: tools defined above and removed for brevity - -# Define an async function to encapsulate the async operation -async def main(): - client = AsyncClient(base_url="http://localhost:3000") - - # Use 'await' to wait for the async method 'chat' to complete - response = await client.chat( - max_tokens=100, - seed=1, - tools=tools, - presence_penalty=-1.1, - messages=[ - { - "role": "system", - "content": "You're a helpful assistant! Answer the users question best you can.", - }, - { - "role": "user", - "content": "What is the weather like in Brooklyn, New York?", - }, - ], - ) - - # Once the response is received, you can process it - print(response.choices[0].message.tool_calls) - -# Ensure the main async function is run in the event loop -if __name__ == "__main__": - import asyncio - asyncio.run(main()) - -# {"id":"","object":"text_completion","created":1709051942,"model":"HuggingFaceH4/zephyr-7b-beta","system_fingerprint":"1.4.3-native","choices":[{"index":0,"message":{"role":"assistant","tool_calls":{"id":0,"type":"function","function":{"description":null,"name":"tools","parameters":{"format":"celsius","location":"New York"}}}},"logprobs":null,"finish_reason":"eos_token"}],"usage":{"prompt_tokens":157,"completion_tokens":20,"total_tokens":177}} - -``` - -### OpenAI integration - -TGI exposes an OpenAI-compatible API, which means you can use OpenAI's client libraries to interact with TGI's Messages API and Tool functions. - -However there are some minor differences in the API, for example `tool_choice="auto"` will ALWAYS choose the tool for you. This is different from OpenAI's API where `tool_choice="auto"` will choose a tool if the model thinks it's necessary. - -```python -from openai import OpenAI - -# Initialize the client, pointing it to one of the available models -client = OpenAI( - base_url="http://localhost:3000/v1", - api_key="_", -) - -# NOTE: tools defined above and removed for brevity - -chat_completion = client.chat.completions.create( - model="tgi", - messages=[ - { - "role": "system", - "content": "Don't make assumptions about what values to plug into functions. Ask for clarification if a user request is ambiguous.", - }, - { - "role": "user", - "content": "What's the weather like the next 3 days in San Francisco, CA?", - }, - ], - tools=tools, - tool_choice="auto", # tool selected by model - max_tokens=500, -) - - -called = chat_completion.choices[0].message.tool_calls -print(called) -# { -# "id": 0, -# "type": "function", -# "function": { -# "description": None, -# "name": "tools", -# "parameters": { -# "format": "celsius", -# "location": "San Francisco, CA", -# "num_days": 3, -# }, -# }, -# } -``` +- If you are using the `/generate` with a `grammar` it is recommended to include the grammar in the prompt prefixed by something like `Please use the following JSON schema to generate the output:`. This will help the model understand the context of the grammar and generate the output accordingly. +- If you are getting a response with many repeated tokens, please use the `frequency_penalty` or `repetition_penalty` to reduce the number of repeated tokens in the output. From 27b3a2c9fc3fd85e8c52ac0ed9c5a2aefe395f97 Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Wed, 1 May 2024 18:21:17 +0200 Subject: [PATCH 21/22] Fix: "Fixing" double BOS for mistral too. (#1843) # What does this PR do? Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. --- server/text_generation_server/models/flash_mistral.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/server/text_generation_server/models/flash_mistral.py b/server/text_generation_server/models/flash_mistral.py index 6959e2ec..85e93543 100644 --- a/server/text_generation_server/models/flash_mistral.py +++ b/server/text_generation_server/models/flash_mistral.py @@ -121,6 +121,11 @@ class FlashMistralBatch(FlashCausalLMBatch): requests_idx_mapping[r.id] = i tokenized_input = tokenized_input[-r.truncate :] + if ( + tokenized_input[0] == tokenizer.bos_token_id + and tokenized_input[1] == tokenizer.bos_token_id + ): + tokenized_input = tokenized_input[1:] input_length = len(tokenized_input) input_lengths.append(input_length) From 0038e6020fec4650ce6c35de37440ab7c7bb206e Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Wed, 1 May 2024 21:48:06 +0200 Subject: [PATCH 22/22] Adding scripts to prepare load data. (#1841) # What does this PR do? Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. --- .gitignore | 1 + load_tests/Makefile | 9 ++++++ load_tests/filter.py | 26 +++++++++++++++ load_tests/orca.py | 27 ++++++++++++++++ load_tests/starcoder_load.js | 63 ------------------------------------ 5 files changed, 63 insertions(+), 63 deletions(-) create mode 100644 load_tests/Makefile create mode 100644 load_tests/filter.py create mode 100644 load_tests/orca.py delete mode 100644 load_tests/starcoder_load.js diff --git a/.gitignore b/.gitignore index 2ac2f6b4..e9ad1808 100644 --- a/.gitignore +++ b/.gitignore @@ -13,3 +13,4 @@ server/exllama_kernels/exllama_kernels/hip_buffers.cuh server/exllama_kernels/exllama_kernels/exllama_ext_hip.cpp data/ +load_tests/*.json diff --git a/load_tests/Makefile b/load_tests/Makefile new file mode 100644 index 00000000..9199aa3b --- /dev/null +++ b/load_tests/Makefile @@ -0,0 +1,9 @@ + +ShareGPT_V3_unfiltered_cleaned_split.json: + wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json + +prepare_share: ShareGPT_V3_unfiltered_cleaned_split.json + python filter.py + +prepare_orca: + python orca.py diff --git a/load_tests/filter.py b/load_tests/filter.py new file mode 100644 index 00000000..a00226ed --- /dev/null +++ b/load_tests/filter.py @@ -0,0 +1,26 @@ +import json + + +def main(): + with open("./ShareGPT_V3_unfiltered_cleaned_split.json", "r") as f: + data = json.load(f) + + # Select only the first 2k conversations that start with a human. + max = 2000 + conversations = [] + for conversation in data: + conv = conversation.get("conversations") + if conv and conv[0]["from"] == "human": + # Trim the rest of the output + conversation["conversations"] = conversation["conversations"][:1] + conversations.append(conversation) + + if len(conversation) >= max: + break + + with open("./small.json", "w") as f: + data = json.dump(conversations, f, indent=4) + + +if __name__ == "__main__": + main() diff --git a/load_tests/orca.py b/load_tests/orca.py new file mode 100644 index 00000000..e607d27c --- /dev/null +++ b/load_tests/orca.py @@ -0,0 +1,27 @@ +import json +import datasets +import tqdm + + +def main(): + dataset = datasets.load_dataset("Open-Orca/OpenOrca", split="train") + # Select only the first 2k conversations that start with a human. + max = min(2000, len(dataset)) + conversations = [] + for item in tqdm.tqdm(dataset, total=max): + conversation = { + "conversations": [ + {"from": "human", "value": item["question"]}, + ], + "id": item["id"], + } + conversations.append(conversation) + if len(conversations) >= max: + break + + with open("./small.json", "w") as f: + data = json.dump(conversations, f, indent=4) + + +if __name__ == "__main__": + main() diff --git a/load_tests/starcoder_load.js b/load_tests/starcoder_load.js deleted file mode 100644 index 2f6cb3d6..00000000 --- a/load_tests/starcoder_load.js +++ /dev/null @@ -1,63 +0,0 @@ -import {check} from 'k6'; -import http from 'k6/http'; -import {Trend} from 'k6/metrics'; - -const host = __ENV.HOST || '127.0.0.1:3000'; - -const totalTime = new Trend('total_time', true); -const validationTime = new Trend('validation_time', true); -const queueTime = new Trend('queue_time', true); -const inferenceTime = new Trend('inference_time', true); -const timePerToken = new Trend('time_per_token', true); - -const example = { - payload: JSON.stringify({ - inputs: '# This is a fibonacci function written in the Python programming language.' + - 'def fibonacci', - parameters: { - details: true, - max_new_tokens: 60, - temperature: 0.2, - top_p: 0.95, - seed: 0, - }, - }), - generated_tokens: 60 -}; - -export const options = { - thresholds: { - http_req_failed: ['rate==0'], - time_per_token: ['p(95)<90'], - queue_time: ['p(95)<1500'], - }, - scenarios: { - load_test: { - executor: 'constant-arrival-rate', - duration: '60s', - preAllocatedVUs: 100, - rate: 10, - timeUnit: '1s', - }, - }, -}; - -export default function () { - const headers = {'Content-Type': 'application/json'}; - const res = http.post(`http://${host}/generate`, example.payload, { - headers, - }); - - check(res, { - 'Post status is 200': (r) => res.status === 200, - 'Post response generated tokens': (r) => res.status === 200 && res.json().details.generated_tokens === example.generated_tokens, - }); - - if (res.status === 200) { - totalTime.add(res.headers["X-Total-Time"]); - validationTime.add(res.headers["X-Validation-Time"]); - queueTime.add(res.headers["X-Queue-Time"]); - inferenceTime.add(res.headers["X-Inference-Time"]); - timePerToken.add(res.headers["X-Time-Per-Token"]); - } -}