mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-06-19 15:52:08 +00:00
Using the "lockfile".
This commit is contained in:
Nicolas Patry
parent
c1cf36c0dc
commit
951eb62b56
@ -233,9 +233,8 @@ COPY server/Makefile server/Makefile
|
||||
ENV UV_SYSTEM_PYTHON=1
|
||||
RUN cd server && \
|
||||
make gen-server && \
|
||||
python -c "from text_generation_server.pb import generate_pb2" && \
|
||||
pip install -U pip uv && \
|
||||
uv pip install -e ".[attention, bnb, accelerate, compressed-tensors, marlin, moe, quantize, peft, outlines]" --no-cache-dir # && \
|
||||
uv pip install -r requirements_cuda.txt
|
||||
# uv pip install nvidia-nccl-cu12==2.22.3
|
||||
|
||||
ENV LD_PRELOAD=/opt/conda/lib/python3.11/site-packages/nvidia/nccl/lib/libnccl.so.2
|
||||
|
||||
@ -1,5 +1,5 @@
|
||||
# Rust builder
|
||||
FROM lukemathwalker/cargo-chef:latest-rust-1.84.0 AS chef
|
||||
FROM lukemathwalker/cargo-chef:latest-rust-1.80.1 AS chef
|
||||
WORKDIR /usr/src
|
||||
|
||||
ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse
|
||||
@ -104,7 +104,7 @@ RUN case ${TARGETPLATFORM} in \
|
||||
/opt/conda/bin/conda clean -ya
|
||||
|
||||
# Install flash-attention, torch dependencies
|
||||
RUN python3 -m pip install --upgrade pip uv && pip install numpy einops ninja joblib msgpack cmake --no-cache-dir && rm -rf /var/lib/apt/lists/*
|
||||
RUN python3 -m pip install --upgrade pip && pip install numpy einops ninja joblib msgpack cmake --no-cache-dir && rm -rf /var/lib/apt/lists/*
|
||||
|
||||
RUN conda install mkl=2021
|
||||
ENV LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/rocm/lib/:/opt/conda/lib/python3.11/site-packages/torch/lib:/opt/conda/lib/
|
||||
@ -234,7 +234,6 @@ FROM kernel-builder AS vllm-builder
|
||||
WORKDIR /usr/src
|
||||
|
||||
COPY server/Makefile-vllm Makefile
|
||||
RUN pip install setuptools_scm
|
||||
|
||||
# Build specific version of vllm
|
||||
RUN make build-vllm-rocm
|
||||
@ -268,24 +267,6 @@ COPY server/exllamav2_kernels/ .
|
||||
|
||||
RUN python setup.py build
|
||||
|
||||
FROM kernel-builder AS marlin-kernels
|
||||
WORKDIR /usr/src
|
||||
ENV MARLIN_KERNELS_BRANCH=v0.3.6
|
||||
ENV VLLM_TARGET_DEVICE=rocm
|
||||
RUN git clone https://github.com/danieldk/marlin-kernels.git && \
|
||||
cd marlin-kernels && \
|
||||
git checkout ${MARLIN_KERNELS_BRANCH} && \
|
||||
python setup.py install
|
||||
|
||||
FROM kernel-builder AS moe-kernels
|
||||
WORKDIR /usr/src
|
||||
ENV MOE_KERNELS_BRANCH=v0.8.2
|
||||
ENV VLLM_TARGET_DEVICE=rocm
|
||||
RUN git clone https://github.com/danieldk/moe-kernels.git && \
|
||||
cd moe-kernels && \
|
||||
git checkout ${MOE_KERNELS_BRANCH} && \
|
||||
python setup.py install
|
||||
|
||||
FROM install_deps AS base-copy
|
||||
|
||||
# Text Generation Inference base env
|
||||
@ -308,21 +289,14 @@ COPY --from=exllama-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-311
|
||||
# Copy build artifacts from exllamav2 kernels builder
|
||||
COPY --from=exllamav2-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
|
||||
|
||||
# Copy build artifacts from marlin kernels
|
||||
COPY --from=marlin-kernels /usr/src/marlin-kernels/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
|
||||
|
||||
# Copy build artifacts from moe kernels
|
||||
COPY --from=moe-kernels /usr/src/moe-kernels/build/lib.linux-x86_64-cpython-311 /opt/conda/lib/python3.11/site-packages
|
||||
|
||||
# Install server
|
||||
COPY proto proto
|
||||
COPY server server
|
||||
COPY server/Makefile server/Makefile
|
||||
ENV UV_SYSTEM_PYTHON=1
|
||||
RUN cd server && \
|
||||
make gen-server && \
|
||||
pip install -U pip uv && \
|
||||
uv pip install -e ".[accelerate, compressed-tensors, peft, outlines]" --no-cache-dir
|
||||
pip install -r requirements_rocm.txt --no-cache-dir
|
||||
# pip install ".[accelerate, compressed-tensors, peft, outlines]" --no-cache-dir
|
||||
|
||||
# Install benchmarker
|
||||
COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
ARG PLATFORM=xpu
|
||||
|
||||
FROM lukemathwalker/cargo-chef:latest-rust-1.84.0 AS chef
|
||||
FROM lukemathwalker/cargo-chef:latest-rust-1.80.1 AS chef
|
||||
WORKDIR /usr/src
|
||||
|
||||
ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse
|
||||
@ -97,10 +97,11 @@ ENV HF_HOME=/data \
|
||||
|
||||
|
||||
WORKDIR /usr/src
|
||||
RUN pip install https://intel-optimized-pytorch.s3.cn-north-1.amazonaws.com.cn/ipex_dev/xpu/torch-2.5.0a0%2Bgite84e33f-cp311-cp311-linux_x86_64.whl --no-cache-dir
|
||||
RUN pip install https://intel-optimized-pytorch.s3.cn-north-1.amazonaws.com.cn/ipex_dev/xpu/torchaudio-2.5.0a0%2B56bc006-cp311-cp311-linux_x86_64.whl --no-cache-dir
|
||||
RUN pip install https://intel-optimized-pytorch.s3.cn-north-1.amazonaws.com.cn/ipex_dev/xpu/torchvision-0.20.0a0%2B8e8a208-cp311-cp311-linux_x86_64.whl --no-cache-dir
|
||||
RUN pip install https://intel-optimized-pytorch.s3.cn-north-1.amazonaws.com.cn/ipex_dev/xpu/oneccl_bind_pt-2.5.0%2Bxpu-cp311-cp311-linux_x86_64.whl --no-cache-dir
|
||||
RUN pip install https://intel-extension-for-pytorch.s3.us-east-1.amazonaws.com/ipex_dev/xpu/torch-2.5.0a0%2Bgite84e33f-cp311-cp311-linux_x86_64.whl --no-cache-dir
|
||||
RUN pip install https://intel-extension-for-pytorch.s3.us-east-1.amazonaws.com/ipex_dev/xpu/torchaudio-2.5.0a0%2B56bc006-cp311-cp311-linux_x86_64.whl --no-cache-dir
|
||||
RUN pip install https://intel-extension-for-pytorch.s3.us-east-1.amazonaws.com/ipex_dev/xpu/torchvision-0.20.0a0%2B8e8a208-cp311-cp311-linux_x86_64.whl --no-cache-dir
|
||||
RUN pip install https://intel-extension-for-pytorch.s3.us-east-1.amazonaws.com/ipex_dev/xpu/intel_extension_for_pytorch-2.5.10%2Bgit9d489a8-cp311-cp311-linux_x86_64.whl --no-cache-dir
|
||||
RUN pip install https://intel-extension-for-pytorch.s3.us-east-1.amazonaws.com/ipex_dev/xpu/oneccl_bind_pt-2.5.0%2Bxpu-cp311-cp311-linux_x86_64.whl --no-cache-dir
|
||||
|
||||
RUN pip install triton-xpu==3.0.0b2 --no-cache-dir
|
||||
|
||||
@ -108,20 +109,15 @@ RUN pip install triton-xpu==3.0.0b2 --no-cache-dir
|
||||
COPY proto proto
|
||||
COPY server server
|
||||
COPY server/Makefile server/Makefile
|
||||
ENV UV_SYSTEM_PYTHON=1
|
||||
RUN cd server && \
|
||||
make gen-server && \
|
||||
pip install -U pip uv && \
|
||||
uv pip install -e ".[accelerate, compressed-tensors, peft, outlines]" --no-cache-dir
|
||||
pip install -r requirements_intel.txt && \
|
||||
pip install ".[accelerate, compressed-tensors, peft, outlines]" --no-cache-dir
|
||||
|
||||
ENV LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/opt/intel/oneapi/pti/0.9/lib:/opt/conda/lib
|
||||
ENV CCL_ZE_IPC_EXCHANGE=sockets
|
||||
#ENV TORCH_LLM_ALLREDUCE=1
|
||||
#ENV CCL_TOPO_FABRIC_VERTEX_CONNECTION_CHECK=0
|
||||
ENV TORCH_DEVICE_BACKEND_AUTOLOAD=0
|
||||
|
||||
RUN git clone https://github.com/intel/intel-extension-for-pytorch && cd intel-extension-for-pytorch && git checkout 1ccf72b2d11cd00b47aef6d6cd054c088aa6f083
|
||||
RUN cd intel-extension-for-pytorch && git submodule update --init --recursive && USE_AOT_DEVLIST='pvc,ats-m150' BUILD_SEPARATE_OPS=OFF BUILD_WITH_CPU=OFF USE_XETLA=ON python setup.py install && rm -rf /usr/src/intel-extension-for-pytorch
|
||||
|
||||
# Install benchmarker
|
||||
COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark
|
||||
@ -213,11 +209,10 @@ ENV LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/opt/conda/lib/"
|
||||
COPY proto proto
|
||||
COPY server server
|
||||
COPY server/Makefile server/Makefile
|
||||
ENV UV_SYSTEM_PYTHON=1
|
||||
RUN cd server && \
|
||||
make gen-server && \
|
||||
pip install -U pip uv && \
|
||||
uv pip install -e ".[accelerate, compressed-tensors, peft, outlines]" --no-cache-dir
|
||||
uv pip install -r requirements_intel.txt --no-cache-dir
|
||||
# pip install ".[accelerate, compressed-tensors, peft, outlines]" --no-cache-dir
|
||||
|
||||
# Install benchmarker
|
||||
COPY --from=builder /usr/src/target/release-opt/text-generation-benchmark /usr/local/bin/text-generation-benchmark
|
||||
@ -227,9 +222,9 @@ COPY --from=builder /usr/src/target/release-opt/text-generation-router /usr/loca
|
||||
COPY --from=builder /usr/src/target/release-opt/text-generation-launcher /usr/local/bin/text-generation-launcher
|
||||
|
||||
FROM ${PLATFORM} AS final
|
||||
ENV ATTENTION=flashdecoding-ipex
|
||||
ENV PREFIX_CACHING=1
|
||||
ENV PREFILL_CHUNKING=1
|
||||
ENV ATTENTION=paged
|
||||
ENV PREFIX_CACHING=0
|
||||
ENV PREFILL_CHUNKING=0
|
||||
ENV CUDA_GRAPHS=0
|
||||
ENTRYPOINT ["text-generation-launcher"]
|
||||
CMD ["--json-output"]
|
||||
|
||||
@ -35,3 +35,8 @@ install-cuda: install-server install-flash-attention-v2-cuda install-flash-atten
|
||||
uv pip install nvidia-nccl-cu12==2.22.3
|
||||
|
||||
install-rocm: install-server install-flash-attention-v2-rocm install-vllm-rocm
|
||||
|
||||
export-requirements:
|
||||
uv pip compile pyproject.toml --extra attention --extra bnb --extra accelerate --extra compressed-tensors --extra marlin --extra moe --extra quantize --extra peft --extra outlines -o requirements_cuda.txt
|
||||
uv pip compile pyproject.toml --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines -o requirements_intel.txt
|
||||
uv pip compile pyproject.toml --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines -o requirements_rocm.txt
|
||||
|
||||
@ -1,55 +1,385 @@
|
||||
certifi==2024.8.30 ; python_version >= "3.9" and python_version < "3.13"
|
||||
charset-normalizer==3.4.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
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==0.8.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
filelock==3.16.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
fsspec==2024.6.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
googleapis-common-protos==1.65.0 ; 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==1.62.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio-status==1.62.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio==1.68.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
hf-transfer==0.1.8 ; python_version >= "3.9" and python_version < "3.13"
|
||||
huggingface-hub==0.23.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
idna==3.10 ; python_version >= "3.9" and python_version < "3.13"
|
||||
importlib-metadata==7.1.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
loguru==0.7.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
markdown-it-py==3.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
mdurl==0.1.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
numpy==1.26.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-api==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-exporter-otlp-proto-common==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-exporter-otlp-proto-grpc==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-exporter-otlp-proto-http==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-exporter-otlp==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-instrumentation-grpc==0.48b0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-instrumentation==0.48b0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-proto==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-sdk==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-semantic-conventions==0.48b0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
packaging==24.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pillow==11.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
prometheus-client==0.20.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
protobuf==4.25.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pygments==2.18.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pyyaml==6.0.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
regex==2024.9.11 ; python_version >= "3.9" and python_version < "3.13"
|
||||
requests==2.32.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
rich==13.9.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
safetensors==0.4.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
scipy==1.13.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
sentencepiece==0.2.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
setuptools==75.2.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
shellingham==1.5.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
tokenizers==0.20.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
tqdm==4.66.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
transformers==4.46.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
typer==0.12.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
typing-extensions==4.12.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
urllib3==2.2.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
win32-setctime==1.1.0 ; python_version >= "3.9" and python_version < "3.13" and sys_platform == "win32"
|
||||
wrapt==1.16.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
zipp==3.20.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
# This file was autogenerated by uv via the following command:
|
||||
# uv pip compile pyproject.toml --extra attention --extra bnb --extra accelerate --extra compressed-tensors --extra marlin --extra moe --extra quantize --extra peft --extra outlines -o requirements_cuda.txt
|
||||
accelerate==1.3.0
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# peft
|
||||
aiohappyeyeballs==2.4.4
|
||||
# via aiohttp
|
||||
aiohttp==3.11.11
|
||||
# via
|
||||
# datasets
|
||||
# fsspec
|
||||
aiosignal==1.3.2
|
||||
# via aiohttp
|
||||
airportsdata==20241001
|
||||
# via outlines
|
||||
annotated-types==0.7.0
|
||||
# via pydantic
|
||||
attention-kernels @ https://github.com/danieldk/attention-kernels/releases/download/v0.2.0.post2/attention_kernels-0.2.0.post2+cu123torch2.5-cp39-abi3-linux_x86_64.whl
|
||||
# via text-generation-server (pyproject.toml)
|
||||
attrs==25.1.0
|
||||
# via
|
||||
# aiohttp
|
||||
# jsonschema
|
||||
# referencing
|
||||
bitsandbytes==0.45.1
|
||||
# via text-generation-server (pyproject.toml)
|
||||
certifi==2024.8.30
|
||||
# via requests
|
||||
charset-normalizer==3.4.0
|
||||
# via requests
|
||||
click==8.1.7
|
||||
# via typer
|
||||
cloudpickle==3.1.1
|
||||
# via outlines
|
||||
compressed-tensors==0.9.1
|
||||
# via text-generation-server (pyproject.toml)
|
||||
datasets==2.21.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
deprecated==1.2.14
|
||||
# via
|
||||
# opentelemetry-api
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
# opentelemetry-semantic-conventions
|
||||
dill==0.3.8
|
||||
# via
|
||||
# datasets
|
||||
# multiprocess
|
||||
diskcache==5.6.3
|
||||
# via outlines
|
||||
einops==0.8.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
filelock==3.16.1
|
||||
# via
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# torch
|
||||
# transformers
|
||||
frozenlist==1.5.0
|
||||
# via
|
||||
# aiohttp
|
||||
# aiosignal
|
||||
fsspec==2024.6.1
|
||||
# via
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# torch
|
||||
genson==1.3.0
|
||||
# via outlines
|
||||
googleapis-common-protos==1.65.0
|
||||
# via
|
||||
# grpcio-status
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
grpc-interceptor==0.15.4
|
||||
# via text-generation-server (pyproject.toml)
|
||||
grpcio==1.68.0
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# grpc-interceptor
|
||||
# grpcio-reflection
|
||||
# grpcio-status
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
grpcio-reflection==1.68.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
grpcio-status==1.68.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
hf-transfer==0.1.8
|
||||
# via text-generation-server (pyproject.toml)
|
||||
huggingface-hub==0.28.1
|
||||
# via
|
||||
# accelerate
|
||||
# datasets
|
||||
# peft
|
||||
# tokenizers
|
||||
# transformers
|
||||
idna==3.10
|
||||
# via
|
||||
# requests
|
||||
# yarl
|
||||
importlib-metadata==7.1.0
|
||||
# via opentelemetry-api
|
||||
interegular==0.3.3
|
||||
# via
|
||||
# outlines
|
||||
# outlines-core
|
||||
jinja2==3.1.5
|
||||
# via
|
||||
# outlines
|
||||
# torch
|
||||
jsonschema==4.23.0
|
||||
# via
|
||||
# outlines
|
||||
# outlines-core
|
||||
jsonschema-specifications==2024.10.1
|
||||
# via jsonschema
|
||||
lark==1.2.2
|
||||
# via outlines
|
||||
loguru==0.7.3
|
||||
# via text-generation-server (pyproject.toml)
|
||||
markdown-it-py==3.0.0
|
||||
# via rich
|
||||
markupsafe==3.0.2
|
||||
# via jinja2
|
||||
marlin-kernels @ https://github.com/danieldk/marlin-kernels/releases/download/v0.3.7/marlin_kernels-0.3.7+cu123torch2.5-cp312-cp312-linux_x86_64.whl
|
||||
# via text-generation-server (pyproject.toml)
|
||||
mdurl==0.1.2
|
||||
# via markdown-it-py
|
||||
moe-kernels @ https://github.com/danieldk/moe-kernels/releases/download/v0.8.2/moe_kernels-0.8.2+cu123torch2.5-cp39-abi3-linux_x86_64.whl
|
||||
# via text-generation-server (pyproject.toml)
|
||||
mpmath==1.3.0
|
||||
# via sympy
|
||||
multidict==6.1.0
|
||||
# via
|
||||
# aiohttp
|
||||
# yarl
|
||||
multiprocess==0.70.16
|
||||
# via datasets
|
||||
nest-asyncio==1.6.0
|
||||
# via outlines
|
||||
networkx==3.4.2
|
||||
# via torch
|
||||
numpy==1.26.4
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# accelerate
|
||||
# bitsandbytes
|
||||
# datasets
|
||||
# outlines
|
||||
# pandas
|
||||
# peft
|
||||
# scipy
|
||||
# transformers
|
||||
nvidia-cublas-cu12==12.4.5.8
|
||||
# via
|
||||
# nvidia-cudnn-cu12
|
||||
# nvidia-cusolver-cu12
|
||||
# torch
|
||||
nvidia-cuda-cupti-cu12==12.4.127
|
||||
# via torch
|
||||
nvidia-cuda-nvrtc-cu12==12.4.127
|
||||
# via torch
|
||||
nvidia-cuda-runtime-cu12==12.4.127
|
||||
# via torch
|
||||
nvidia-cudnn-cu12==9.1.0.70
|
||||
# via torch
|
||||
nvidia-cufft-cu12==11.2.1.3
|
||||
# via torch
|
||||
nvidia-curand-cu12==10.3.5.147
|
||||
# via torch
|
||||
nvidia-cusolver-cu12==11.6.1.9
|
||||
# via torch
|
||||
nvidia-cusparse-cu12==12.3.1.170
|
||||
# via
|
||||
# nvidia-cusolver-cu12
|
||||
# torch
|
||||
nvidia-cusparselt-cu12==0.6.2
|
||||
# via torch
|
||||
nvidia-ml-py==12.570.86
|
||||
# via moe-kernels
|
||||
nvidia-nccl-cu12==2.21.5
|
||||
# via torch
|
||||
nvidia-nvjitlink-cu12==12.4.127
|
||||
# via
|
||||
# nvidia-cusolver-cu12
|
||||
# nvidia-cusparse-cu12
|
||||
# torch
|
||||
nvidia-nvtx-cu12==12.4.127
|
||||
# via torch
|
||||
opentelemetry-api==1.30.0
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
# opentelemetry-instrumentation
|
||||
# opentelemetry-instrumentation-grpc
|
||||
# opentelemetry-sdk
|
||||
# opentelemetry-semantic-conventions
|
||||
opentelemetry-exporter-otlp==1.30.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
opentelemetry-exporter-otlp-proto-common==1.30.0
|
||||
# via
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
opentelemetry-exporter-otlp-proto-grpc==1.30.0
|
||||
# via opentelemetry-exporter-otlp
|
||||
opentelemetry-exporter-otlp-proto-http==1.30.0
|
||||
# via opentelemetry-exporter-otlp
|
||||
opentelemetry-instrumentation==0.51b0
|
||||
# via opentelemetry-instrumentation-grpc
|
||||
opentelemetry-instrumentation-grpc==0.51b0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
opentelemetry-proto==1.30.0
|
||||
# via
|
||||
# opentelemetry-exporter-otlp-proto-common
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
opentelemetry-sdk==1.30.0
|
||||
# via
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
opentelemetry-semantic-conventions==0.51b0
|
||||
# via
|
||||
# opentelemetry-instrumentation
|
||||
# opentelemetry-instrumentation-grpc
|
||||
# opentelemetry-sdk
|
||||
outlines==0.1.14
|
||||
# via text-generation-server (pyproject.toml)
|
||||
outlines-core==0.1.26
|
||||
# via outlines
|
||||
packaging==24.1
|
||||
# via
|
||||
# accelerate
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# opentelemetry-instrumentation
|
||||
# peft
|
||||
# transformers
|
||||
pandas==2.2.3
|
||||
# via datasets
|
||||
peft==0.14.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
pillow==11.1.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
prometheus-client==0.21.1
|
||||
# via text-generation-server (pyproject.toml)
|
||||
propcache==0.2.1
|
||||
# via
|
||||
# aiohttp
|
||||
# yarl
|
||||
protobuf==5.29.3
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# googleapis-common-protos
|
||||
# grpcio-reflection
|
||||
# grpcio-status
|
||||
# opentelemetry-proto
|
||||
psutil==6.1.1
|
||||
# via
|
||||
# accelerate
|
||||
# peft
|
||||
py-cpuinfo==9.0.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
pyarrow==19.0.0
|
||||
# via datasets
|
||||
pycountry==24.6.1
|
||||
# via outlines
|
||||
pydantic==2.10.6
|
||||
# via
|
||||
# compressed-tensors
|
||||
# outlines
|
||||
pydantic-core==2.27.2
|
||||
# via pydantic
|
||||
pygments==2.18.0
|
||||
# via rich
|
||||
python-dateutil==2.9.0.post0
|
||||
# via pandas
|
||||
pytz==2025.1
|
||||
# via pandas
|
||||
pyyaml==6.0.2
|
||||
# via
|
||||
# accelerate
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# peft
|
||||
# transformers
|
||||
referencing==0.36.2
|
||||
# via
|
||||
# jsonschema
|
||||
# jsonschema-specifications
|
||||
# outlines
|
||||
regex==2024.9.11
|
||||
# via transformers
|
||||
requests==2.32.3
|
||||
# via
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
# outlines
|
||||
# transformers
|
||||
rich==13.9.4
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# typer
|
||||
rpds-py==0.22.3
|
||||
# via
|
||||
# jsonschema
|
||||
# referencing
|
||||
safetensors==0.4.5
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# accelerate
|
||||
# peft
|
||||
# transformers
|
||||
scipy==1.13.1
|
||||
# via text-generation-server (pyproject.toml)
|
||||
sentencepiece==0.2.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
setuptools==75.2.0
|
||||
# via torch
|
||||
shellingham==1.5.4
|
||||
# via typer
|
||||
six==1.17.0
|
||||
# via python-dateutil
|
||||
sympy==1.13.1
|
||||
# via torch
|
||||
texttable==1.7.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
tokenizers==0.20.3
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# transformers
|
||||
torch==2.6.0
|
||||
# via
|
||||
# accelerate
|
||||
# attention-kernels
|
||||
# bitsandbytes
|
||||
# compressed-tensors
|
||||
# marlin-kernels
|
||||
# moe-kernels
|
||||
# outlines
|
||||
# peft
|
||||
tqdm==4.66.5
|
||||
# via
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# outlines
|
||||
# peft
|
||||
# transformers
|
||||
transformers==4.46.3
|
||||
# via
|
||||
# compressed-tensors
|
||||
# peft
|
||||
triton==3.2.0
|
||||
# via
|
||||
# moe-kernels
|
||||
# torch
|
||||
typer==0.15.1
|
||||
# via text-generation-server (pyproject.toml)
|
||||
typing-extensions==4.12.2
|
||||
# via
|
||||
# huggingface-hub
|
||||
# opentelemetry-sdk
|
||||
# outlines
|
||||
# pydantic
|
||||
# pydantic-core
|
||||
# referencing
|
||||
# torch
|
||||
# typer
|
||||
tzdata==2025.1
|
||||
# via pandas
|
||||
urllib3==2.2.3
|
||||
# via requests
|
||||
wrapt==1.16.0
|
||||
# via
|
||||
# deprecated
|
||||
# opentelemetry-instrumentation
|
||||
# opentelemetry-instrumentation-grpc
|
||||
xxhash==3.5.0
|
||||
# via datasets
|
||||
yarl==1.18.3
|
||||
# via aiohttp
|
||||
zipp==3.20.2
|
||||
# via importlib-metadata
|
||||
|
||||
@ -1,55 +1,368 @@
|
||||
certifi==2024.8.30 ; python_version >= "3.9" and python_version < "3.13"
|
||||
charset-normalizer==3.4.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
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==0.8.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
filelock==3.16.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
fsspec==2024.6.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
googleapis-common-protos==1.65.0 ; 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==1.62.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio-status==1.62.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio==1.68.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
hf-transfer==0.1.8 ; python_version >= "3.9" and python_version < "3.13"
|
||||
huggingface-hub==0.23.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
idna==3.10 ; python_version >= "3.9" and python_version < "3.13"
|
||||
importlib-metadata==7.1.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
loguru==0.7.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
markdown-it-py==3.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
mdurl==0.1.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
numpy==1.26.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-api==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-exporter-otlp-proto-common==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-exporter-otlp-proto-grpc==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-exporter-otlp-proto-http==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-exporter-otlp==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-instrumentation-grpc==0.48b0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-instrumentation==0.48b0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-proto==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-sdk==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-semantic-conventions==0.48b0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
packaging==24.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pillow==11.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
prometheus-client==0.20.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
protobuf==4.25.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pygments==2.18.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pyyaml==6.0.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
regex==2024.9.11 ; python_version >= "3.9" and python_version < "3.13"
|
||||
requests==2.32.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
rich==13.9.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
safetensors==0.4.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
scipy==1.13.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
sentencepiece==0.2.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
setuptools==75.2.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
shellingham==1.5.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
tokenizers==0.20.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
tqdm==4.66.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
transformers==4.46.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
typer==0.12.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
typing-extensions==4.12.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
urllib3==2.2.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
win32-setctime==1.1.0 ; python_version >= "3.9" and python_version < "3.13" and sys_platform == "win32"
|
||||
wrapt==1.16.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
zipp==3.20.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
# This file was autogenerated by uv via the following command:
|
||||
# uv pip compile pyproject.toml --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines -o requirements_intel.txt
|
||||
accelerate==1.3.0
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# peft
|
||||
aiohappyeyeballs==2.4.4
|
||||
# via aiohttp
|
||||
aiohttp==3.11.11
|
||||
# via
|
||||
# datasets
|
||||
# fsspec
|
||||
aiosignal==1.3.2
|
||||
# via aiohttp
|
||||
airportsdata==20241001
|
||||
# via outlines
|
||||
annotated-types==0.7.0
|
||||
# via pydantic
|
||||
attrs==25.1.0
|
||||
# via
|
||||
# aiohttp
|
||||
# jsonschema
|
||||
# referencing
|
||||
certifi==2024.8.30
|
||||
# via requests
|
||||
charset-normalizer==3.4.0
|
||||
# via requests
|
||||
click==8.1.7
|
||||
# via typer
|
||||
cloudpickle==3.1.1
|
||||
# via outlines
|
||||
compressed-tensors==0.9.1
|
||||
# via text-generation-server (pyproject.toml)
|
||||
datasets==2.21.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
deprecated==1.2.14
|
||||
# via
|
||||
# opentelemetry-api
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
# opentelemetry-semantic-conventions
|
||||
dill==0.3.8
|
||||
# via
|
||||
# datasets
|
||||
# multiprocess
|
||||
diskcache==5.6.3
|
||||
# via outlines
|
||||
einops==0.8.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
filelock==3.16.1
|
||||
# via
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# torch
|
||||
# transformers
|
||||
frozenlist==1.5.0
|
||||
# via
|
||||
# aiohttp
|
||||
# aiosignal
|
||||
fsspec==2024.6.1
|
||||
# via
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# torch
|
||||
genson==1.3.0
|
||||
# via outlines
|
||||
googleapis-common-protos==1.65.0
|
||||
# via
|
||||
# grpcio-status
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
grpc-interceptor==0.15.4
|
||||
# via text-generation-server (pyproject.toml)
|
||||
grpcio==1.68.0
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# grpc-interceptor
|
||||
# grpcio-reflection
|
||||
# grpcio-status
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
grpcio-reflection==1.68.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
grpcio-status==1.68.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
hf-transfer==0.1.8
|
||||
# via text-generation-server (pyproject.toml)
|
||||
huggingface-hub==0.28.1
|
||||
# via
|
||||
# accelerate
|
||||
# datasets
|
||||
# peft
|
||||
# tokenizers
|
||||
# transformers
|
||||
idna==3.10
|
||||
# via
|
||||
# requests
|
||||
# yarl
|
||||
importlib-metadata==7.1.0
|
||||
# via opentelemetry-api
|
||||
interegular==0.3.3
|
||||
# via
|
||||
# outlines
|
||||
# outlines-core
|
||||
jinja2==3.1.5
|
||||
# via
|
||||
# outlines
|
||||
# torch
|
||||
jsonschema==4.23.0
|
||||
# via
|
||||
# outlines
|
||||
# outlines-core
|
||||
jsonschema-specifications==2024.10.1
|
||||
# via jsonschema
|
||||
lark==1.2.2
|
||||
# via outlines
|
||||
loguru==0.7.3
|
||||
# via text-generation-server (pyproject.toml)
|
||||
markdown-it-py==3.0.0
|
||||
# via rich
|
||||
markupsafe==3.0.2
|
||||
# via jinja2
|
||||
mdurl==0.1.2
|
||||
# via markdown-it-py
|
||||
mpmath==1.3.0
|
||||
# via sympy
|
||||
multidict==6.1.0
|
||||
# via
|
||||
# aiohttp
|
||||
# yarl
|
||||
multiprocess==0.70.16
|
||||
# via datasets
|
||||
nest-asyncio==1.6.0
|
||||
# via outlines
|
||||
networkx==3.4.2
|
||||
# via torch
|
||||
numpy==1.26.4
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# accelerate
|
||||
# datasets
|
||||
# outlines
|
||||
# pandas
|
||||
# peft
|
||||
# scipy
|
||||
# transformers
|
||||
nvidia-cublas-cu12==12.4.5.8
|
||||
# via
|
||||
# nvidia-cudnn-cu12
|
||||
# nvidia-cusolver-cu12
|
||||
# torch
|
||||
nvidia-cuda-cupti-cu12==12.4.127
|
||||
# via torch
|
||||
nvidia-cuda-nvrtc-cu12==12.4.127
|
||||
# via torch
|
||||
nvidia-cuda-runtime-cu12==12.4.127
|
||||
# via torch
|
||||
nvidia-cudnn-cu12==9.1.0.70
|
||||
# via torch
|
||||
nvidia-cufft-cu12==11.2.1.3
|
||||
# via torch
|
||||
nvidia-curand-cu12==10.3.5.147
|
||||
# via torch
|
||||
nvidia-cusolver-cu12==11.6.1.9
|
||||
# via torch
|
||||
nvidia-cusparse-cu12==12.3.1.170
|
||||
# via
|
||||
# nvidia-cusolver-cu12
|
||||
# torch
|
||||
nvidia-cusparselt-cu12==0.6.2
|
||||
# via torch
|
||||
nvidia-nccl-cu12==2.21.5
|
||||
# via torch
|
||||
nvidia-nvjitlink-cu12==12.4.127
|
||||
# via
|
||||
# nvidia-cusolver-cu12
|
||||
# nvidia-cusparse-cu12
|
||||
# torch
|
||||
nvidia-nvtx-cu12==12.4.127
|
||||
# via torch
|
||||
opentelemetry-api==1.30.0
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
# opentelemetry-instrumentation
|
||||
# opentelemetry-instrumentation-grpc
|
||||
# opentelemetry-sdk
|
||||
# opentelemetry-semantic-conventions
|
||||
opentelemetry-exporter-otlp==1.30.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
opentelemetry-exporter-otlp-proto-common==1.30.0
|
||||
# via
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
opentelemetry-exporter-otlp-proto-grpc==1.30.0
|
||||
# via opentelemetry-exporter-otlp
|
||||
opentelemetry-exporter-otlp-proto-http==1.30.0
|
||||
# via opentelemetry-exporter-otlp
|
||||
opentelemetry-instrumentation==0.51b0
|
||||
# via opentelemetry-instrumentation-grpc
|
||||
opentelemetry-instrumentation-grpc==0.51b0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
opentelemetry-proto==1.30.0
|
||||
# via
|
||||
# opentelemetry-exporter-otlp-proto-common
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
opentelemetry-sdk==1.30.0
|
||||
# via
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
opentelemetry-semantic-conventions==0.51b0
|
||||
# via
|
||||
# opentelemetry-instrumentation
|
||||
# opentelemetry-instrumentation-grpc
|
||||
# opentelemetry-sdk
|
||||
outlines==0.1.14
|
||||
# via text-generation-server (pyproject.toml)
|
||||
outlines-core==0.1.26
|
||||
# via outlines
|
||||
packaging==24.1
|
||||
# via
|
||||
# accelerate
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# opentelemetry-instrumentation
|
||||
# peft
|
||||
# transformers
|
||||
pandas==2.2.3
|
||||
# via datasets
|
||||
peft==0.14.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
pillow==11.1.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
prometheus-client==0.21.1
|
||||
# via text-generation-server (pyproject.toml)
|
||||
propcache==0.2.1
|
||||
# via
|
||||
# aiohttp
|
||||
# yarl
|
||||
protobuf==5.29.3
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# googleapis-common-protos
|
||||
# grpcio-reflection
|
||||
# grpcio-status
|
||||
# opentelemetry-proto
|
||||
psutil==6.1.1
|
||||
# via
|
||||
# accelerate
|
||||
# peft
|
||||
py-cpuinfo==9.0.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
pyarrow==19.0.0
|
||||
# via datasets
|
||||
pycountry==24.6.1
|
||||
# via outlines
|
||||
pydantic==2.10.6
|
||||
# via
|
||||
# compressed-tensors
|
||||
# outlines
|
||||
pydantic-core==2.27.2
|
||||
# via pydantic
|
||||
pygments==2.18.0
|
||||
# via rich
|
||||
python-dateutil==2.9.0.post0
|
||||
# via pandas
|
||||
pytz==2025.1
|
||||
# via pandas
|
||||
pyyaml==6.0.2
|
||||
# via
|
||||
# accelerate
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# peft
|
||||
# transformers
|
||||
referencing==0.36.2
|
||||
# via
|
||||
# jsonschema
|
||||
# jsonschema-specifications
|
||||
# outlines
|
||||
regex==2024.9.11
|
||||
# via transformers
|
||||
requests==2.32.3
|
||||
# via
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
# outlines
|
||||
# transformers
|
||||
rich==13.9.4
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# typer
|
||||
rpds-py==0.22.3
|
||||
# via
|
||||
# jsonschema
|
||||
# referencing
|
||||
safetensors==0.4.5
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# accelerate
|
||||
# peft
|
||||
# transformers
|
||||
scipy==1.13.1
|
||||
# via text-generation-server (pyproject.toml)
|
||||
sentencepiece==0.2.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
setuptools==75.2.0
|
||||
# via torch
|
||||
shellingham==1.5.4
|
||||
# via typer
|
||||
six==1.17.0
|
||||
# via python-dateutil
|
||||
sympy==1.13.1
|
||||
# via torch
|
||||
texttable==1.7.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
tokenizers==0.20.3
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# transformers
|
||||
torch==2.6.0
|
||||
# via
|
||||
# accelerate
|
||||
# compressed-tensors
|
||||
# outlines
|
||||
# peft
|
||||
tqdm==4.66.5
|
||||
# via
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# outlines
|
||||
# peft
|
||||
# transformers
|
||||
transformers==4.46.3
|
||||
# via
|
||||
# compressed-tensors
|
||||
# peft
|
||||
triton==3.2.0
|
||||
# via torch
|
||||
typer==0.15.1
|
||||
# via text-generation-server (pyproject.toml)
|
||||
typing-extensions==4.12.2
|
||||
# via
|
||||
# huggingface-hub
|
||||
# opentelemetry-sdk
|
||||
# outlines
|
||||
# pydantic
|
||||
# pydantic-core
|
||||
# referencing
|
||||
# torch
|
||||
# typer
|
||||
tzdata==2025.1
|
||||
# via pandas
|
||||
urllib3==2.2.3
|
||||
# via requests
|
||||
wrapt==1.16.0
|
||||
# via
|
||||
# deprecated
|
||||
# opentelemetry-instrumentation
|
||||
# opentelemetry-instrumentation-grpc
|
||||
xxhash==3.5.0
|
||||
# via datasets
|
||||
yarl==1.18.3
|
||||
# via aiohttp
|
||||
zipp==3.20.2
|
||||
# via importlib-metadata
|
||||
|
||||
@ -1,55 +1,368 @@
|
||||
certifi==2024.8.30 ; python_version >= "3.9" and python_version < "3.13"
|
||||
charset-normalizer==3.4.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
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==0.8.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
filelock==3.16.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
fsspec==2024.6.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
googleapis-common-protos==1.65.0 ; 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==1.62.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio-status==1.62.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
grpcio==1.68.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
hf-transfer==0.1.8 ; python_version >= "3.9" and python_version < "3.13"
|
||||
huggingface-hub==0.23.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
idna==3.10 ; python_version >= "3.9" and python_version < "3.13"
|
||||
importlib-metadata==7.1.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
loguru==0.7.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
markdown-it-py==3.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
mdurl==0.1.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
numpy==1.26.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-api==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-exporter-otlp-proto-common==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-exporter-otlp-proto-grpc==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-exporter-otlp-proto-http==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-exporter-otlp==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-instrumentation-grpc==0.48b0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-instrumentation==0.48b0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-proto==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-sdk==1.27.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
opentelemetry-semantic-conventions==0.48b0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
packaging==24.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pillow==11.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
prometheus-client==0.20.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
protobuf==4.25.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
py-cpuinfo==9.0.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pygments==2.18.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
pyyaml==6.0.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
regex==2024.9.11 ; python_version >= "3.9" and python_version < "3.13"
|
||||
requests==2.32.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
rich==13.9.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
safetensors==0.4.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
scipy==1.13.1 ; python_version >= "3.9" and python_version < "3.13"
|
||||
sentencepiece==0.2.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
setuptools==75.2.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
shellingham==1.5.4 ; python_version >= "3.9" and python_version < "3.13"
|
||||
tokenizers==0.20.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
tqdm==4.66.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
transformers==4.46.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
typer==0.12.5 ; python_version >= "3.9" and python_version < "3.13"
|
||||
typing-extensions==4.12.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
urllib3==2.2.3 ; python_version >= "3.9" and python_version < "3.13"
|
||||
win32-setctime==1.1.0 ; python_version >= "3.9" and python_version < "3.13" and sys_platform == "win32"
|
||||
wrapt==1.16.0 ; python_version >= "3.9" and python_version < "3.13"
|
||||
zipp==3.20.2 ; python_version >= "3.9" and python_version < "3.13"
|
||||
# This file was autogenerated by uv via the following command:
|
||||
# uv pip compile pyproject.toml --extra accelerate --extra compressed-tensors --extra quantize --extra peft --extra outlines -o requirements_rocm.txt
|
||||
accelerate==1.3.0
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# peft
|
||||
aiohappyeyeballs==2.4.4
|
||||
# via aiohttp
|
||||
aiohttp==3.11.11
|
||||
# via
|
||||
# datasets
|
||||
# fsspec
|
||||
aiosignal==1.3.2
|
||||
# via aiohttp
|
||||
airportsdata==20241001
|
||||
# via outlines
|
||||
annotated-types==0.7.0
|
||||
# via pydantic
|
||||
attrs==25.1.0
|
||||
# via
|
||||
# aiohttp
|
||||
# jsonschema
|
||||
# referencing
|
||||
certifi==2024.8.30
|
||||
# via requests
|
||||
charset-normalizer==3.4.0
|
||||
# via requests
|
||||
click==8.1.7
|
||||
# via typer
|
||||
cloudpickle==3.1.1
|
||||
# via outlines
|
||||
compressed-tensors==0.9.1
|
||||
# via text-generation-server (pyproject.toml)
|
||||
datasets==2.21.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
deprecated==1.2.14
|
||||
# via
|
||||
# opentelemetry-api
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
# opentelemetry-semantic-conventions
|
||||
dill==0.3.8
|
||||
# via
|
||||
# datasets
|
||||
# multiprocess
|
||||
diskcache==5.6.3
|
||||
# via outlines
|
||||
einops==0.8.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
filelock==3.16.1
|
||||
# via
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# torch
|
||||
# transformers
|
||||
frozenlist==1.5.0
|
||||
# via
|
||||
# aiohttp
|
||||
# aiosignal
|
||||
fsspec==2024.6.1
|
||||
# via
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# torch
|
||||
genson==1.3.0
|
||||
# via outlines
|
||||
googleapis-common-protos==1.65.0
|
||||
# via
|
||||
# grpcio-status
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
grpc-interceptor==0.15.4
|
||||
# via text-generation-server (pyproject.toml)
|
||||
grpcio==1.68.0
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# grpc-interceptor
|
||||
# grpcio-reflection
|
||||
# grpcio-status
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
grpcio-reflection==1.68.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
grpcio-status==1.68.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
hf-transfer==0.1.8
|
||||
# via text-generation-server (pyproject.toml)
|
||||
huggingface-hub==0.28.1
|
||||
# via
|
||||
# accelerate
|
||||
# datasets
|
||||
# peft
|
||||
# tokenizers
|
||||
# transformers
|
||||
idna==3.10
|
||||
# via
|
||||
# requests
|
||||
# yarl
|
||||
importlib-metadata==7.1.0
|
||||
# via opentelemetry-api
|
||||
interegular==0.3.3
|
||||
# via
|
||||
# outlines
|
||||
# outlines-core
|
||||
jinja2==3.1.5
|
||||
# via
|
||||
# outlines
|
||||
# torch
|
||||
jsonschema==4.23.0
|
||||
# via
|
||||
# outlines
|
||||
# outlines-core
|
||||
jsonschema-specifications==2024.10.1
|
||||
# via jsonschema
|
||||
lark==1.2.2
|
||||
# via outlines
|
||||
loguru==0.7.3
|
||||
# via text-generation-server (pyproject.toml)
|
||||
markdown-it-py==3.0.0
|
||||
# via rich
|
||||
markupsafe==3.0.2
|
||||
# via jinja2
|
||||
mdurl==0.1.2
|
||||
# via markdown-it-py
|
||||
mpmath==1.3.0
|
||||
# via sympy
|
||||
multidict==6.1.0
|
||||
# via
|
||||
# aiohttp
|
||||
# yarl
|
||||
multiprocess==0.70.16
|
||||
# via datasets
|
||||
nest-asyncio==1.6.0
|
||||
# via outlines
|
||||
networkx==3.4.2
|
||||
# via torch
|
||||
numpy==1.26.4
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# accelerate
|
||||
# datasets
|
||||
# outlines
|
||||
# pandas
|
||||
# peft
|
||||
# scipy
|
||||
# transformers
|
||||
nvidia-cublas-cu12==12.4.5.8
|
||||
# via
|
||||
# nvidia-cudnn-cu12
|
||||
# nvidia-cusolver-cu12
|
||||
# torch
|
||||
nvidia-cuda-cupti-cu12==12.4.127
|
||||
# via torch
|
||||
nvidia-cuda-nvrtc-cu12==12.4.127
|
||||
# via torch
|
||||
nvidia-cuda-runtime-cu12==12.4.127
|
||||
# via torch
|
||||
nvidia-cudnn-cu12==9.1.0.70
|
||||
# via torch
|
||||
nvidia-cufft-cu12==11.2.1.3
|
||||
# via torch
|
||||
nvidia-curand-cu12==10.3.5.147
|
||||
# via torch
|
||||
nvidia-cusolver-cu12==11.6.1.9
|
||||
# via torch
|
||||
nvidia-cusparse-cu12==12.3.1.170
|
||||
# via
|
||||
# nvidia-cusolver-cu12
|
||||
# torch
|
||||
nvidia-cusparselt-cu12==0.6.2
|
||||
# via torch
|
||||
nvidia-nccl-cu12==2.21.5
|
||||
# via torch
|
||||
nvidia-nvjitlink-cu12==12.4.127
|
||||
# via
|
||||
# nvidia-cusolver-cu12
|
||||
# nvidia-cusparse-cu12
|
||||
# torch
|
||||
nvidia-nvtx-cu12==12.4.127
|
||||
# via torch
|
||||
opentelemetry-api==1.30.0
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
# opentelemetry-instrumentation
|
||||
# opentelemetry-instrumentation-grpc
|
||||
# opentelemetry-sdk
|
||||
# opentelemetry-semantic-conventions
|
||||
opentelemetry-exporter-otlp==1.30.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
opentelemetry-exporter-otlp-proto-common==1.30.0
|
||||
# via
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
opentelemetry-exporter-otlp-proto-grpc==1.30.0
|
||||
# via opentelemetry-exporter-otlp
|
||||
opentelemetry-exporter-otlp-proto-http==1.30.0
|
||||
# via opentelemetry-exporter-otlp
|
||||
opentelemetry-instrumentation==0.51b0
|
||||
# via opentelemetry-instrumentation-grpc
|
||||
opentelemetry-instrumentation-grpc==0.51b0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
opentelemetry-proto==1.30.0
|
||||
# via
|
||||
# opentelemetry-exporter-otlp-proto-common
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
opentelemetry-sdk==1.30.0
|
||||
# via
|
||||
# opentelemetry-exporter-otlp-proto-grpc
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
opentelemetry-semantic-conventions==0.51b0
|
||||
# via
|
||||
# opentelemetry-instrumentation
|
||||
# opentelemetry-instrumentation-grpc
|
||||
# opentelemetry-sdk
|
||||
outlines==0.1.14
|
||||
# via text-generation-server (pyproject.toml)
|
||||
outlines-core==0.1.26
|
||||
# via outlines
|
||||
packaging==24.1
|
||||
# via
|
||||
# accelerate
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# opentelemetry-instrumentation
|
||||
# peft
|
||||
# transformers
|
||||
pandas==2.2.3
|
||||
# via datasets
|
||||
peft==0.14.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
pillow==11.1.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
prometheus-client==0.21.1
|
||||
# via text-generation-server (pyproject.toml)
|
||||
propcache==0.2.1
|
||||
# via
|
||||
# aiohttp
|
||||
# yarl
|
||||
protobuf==5.29.3
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# googleapis-common-protos
|
||||
# grpcio-reflection
|
||||
# grpcio-status
|
||||
# opentelemetry-proto
|
||||
psutil==6.1.1
|
||||
# via
|
||||
# accelerate
|
||||
# peft
|
||||
py-cpuinfo==9.0.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
pyarrow==19.0.0
|
||||
# via datasets
|
||||
pycountry==24.6.1
|
||||
# via outlines
|
||||
pydantic==2.10.6
|
||||
# via
|
||||
# compressed-tensors
|
||||
# outlines
|
||||
pydantic-core==2.27.2
|
||||
# via pydantic
|
||||
pygments==2.18.0
|
||||
# via rich
|
||||
python-dateutil==2.9.0.post0
|
||||
# via pandas
|
||||
pytz==2025.1
|
||||
# via pandas
|
||||
pyyaml==6.0.2
|
||||
# via
|
||||
# accelerate
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# peft
|
||||
# transformers
|
||||
referencing==0.36.2
|
||||
# via
|
||||
# jsonschema
|
||||
# jsonschema-specifications
|
||||
# outlines
|
||||
regex==2024.9.11
|
||||
# via transformers
|
||||
requests==2.32.3
|
||||
# via
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# opentelemetry-exporter-otlp-proto-http
|
||||
# outlines
|
||||
# transformers
|
||||
rich==13.9.4
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# typer
|
||||
rpds-py==0.22.3
|
||||
# via
|
||||
# jsonschema
|
||||
# referencing
|
||||
safetensors==0.4.5
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# accelerate
|
||||
# peft
|
||||
# transformers
|
||||
scipy==1.13.1
|
||||
# via text-generation-server (pyproject.toml)
|
||||
sentencepiece==0.2.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
setuptools==75.2.0
|
||||
# via torch
|
||||
shellingham==1.5.4
|
||||
# via typer
|
||||
six==1.17.0
|
||||
# via python-dateutil
|
||||
sympy==1.13.1
|
||||
# via torch
|
||||
texttable==1.7.0
|
||||
# via text-generation-server (pyproject.toml)
|
||||
tokenizers==0.20.3
|
||||
# via
|
||||
# text-generation-server (pyproject.toml)
|
||||
# transformers
|
||||
torch==2.6.0
|
||||
# via
|
||||
# accelerate
|
||||
# compressed-tensors
|
||||
# outlines
|
||||
# peft
|
||||
tqdm==4.66.5
|
||||
# via
|
||||
# datasets
|
||||
# huggingface-hub
|
||||
# outlines
|
||||
# peft
|
||||
# transformers
|
||||
transformers==4.46.3
|
||||
# via
|
||||
# compressed-tensors
|
||||
# peft
|
||||
triton==3.2.0
|
||||
# via torch
|
||||
typer==0.15.1
|
||||
# via text-generation-server (pyproject.toml)
|
||||
typing-extensions==4.12.2
|
||||
# via
|
||||
# huggingface-hub
|
||||
# opentelemetry-sdk
|
||||
# outlines
|
||||
# pydantic
|
||||
# pydantic-core
|
||||
# referencing
|
||||
# torch
|
||||
# typer
|
||||
tzdata==2025.1
|
||||
# via pandas
|
||||
urllib3==2.2.3
|
||||
# via requests
|
||||
wrapt==1.16.0
|
||||
# via
|
||||
# deprecated
|
||||
# opentelemetry-instrumentation
|
||||
# opentelemetry-instrumentation-grpc
|
||||
xxhash==3.5.0
|
||||
# via datasets
|
||||
yarl==1.18.3
|
||||
# via aiohttp
|
||||
zipp==3.20.2
|
||||
# via importlib-metadata
|
||||
|
||||
Loading…
Reference in New Issue
Block a user