From 09eca6422788b1710c54ee0d05dd6746f16bb681 Mon Sep 17 00:00:00 2001 From: Nicolas Patry Date: Mon, 14 Aug 2023 11:23:11 +0200 Subject: [PATCH] Version 1.0.1 (#836) # 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. --- Cargo.lock | 8 ++++---- Cargo.toml | 2 +- README.md | 4 ++-- docs/openapi.json | 4 ++-- docs/source/basic_tutorials/gated_model_access.md | 4 ++-- docs/source/quicktour.md | 2 +- server/.gitignore | 5 ++++- server/pyproject.toml | 2 +- 8 files changed, 17 insertions(+), 14 deletions(-) diff --git a/Cargo.lock b/Cargo.lock index 61c22a40..f9cfecf7 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -2893,7 +2893,7 @@ dependencies = [ [[package]] name = "text-generation-benchmark" -version = "1.0.0" +version = "1.0.1" dependencies = [ "average", "clap", @@ -2913,7 +2913,7 @@ dependencies = [ [[package]] name = "text-generation-client" -version = "1.0.0" +version = "1.0.1" dependencies = [ "futures", "grpc-metadata", @@ -2929,7 +2929,7 @@ dependencies = [ [[package]] name = "text-generation-launcher" -version = "1.0.0" +version = "1.0.1" dependencies = [ "clap", "ctrlc", @@ -2945,7 +2945,7 @@ dependencies = [ [[package]] name = "text-generation-router" -version = "1.0.0" +version = "1.0.1" dependencies = [ "async-stream", "axum", diff --git a/Cargo.toml b/Cargo.toml index 255d35d4..1cbac920 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -8,7 +8,7 @@ members = [ ] [workspace.package] -version = "1.0.0" +version = "1.0.1" edition = "2021" authors = ["Olivier Dehaene"] homepage = "https://github.com/huggingface/text-generation-inference" diff --git a/README.md b/README.md index d937e16c..8dcd396b 100644 --- a/README.md +++ b/README.md @@ -83,7 +83,7 @@ The easiest way of getting started is using the official Docker container: model=tiiuae/falcon-7b-instruct volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run -docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.0 --model-id $model +docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.1 --model-id $model ``` **Note:** To use GPUs, you need to install the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html). We also recommend using NVIDIA drivers with CUDA version 11.8 or higher. @@ -150,7 +150,7 @@ model=meta-llama/Llama-2-7b-chat-hf volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run token= -docker run --gpus all --shm-size 1g -e HUGGING_FACE_HUB_TOKEN=$token -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.0 --model-id $model +docker run --gpus all --shm-size 1g -e HUGGING_FACE_HUB_TOKEN=$token -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.1 --model-id $model ``` ### A note on Shared Memory (shm) diff --git a/docs/openapi.json b/docs/openapi.json index 0465a5ad..ab1802c3 100644 --- a/docs/openapi.json +++ b/docs/openapi.json @@ -10,7 +10,7 @@ "name": "Apache 2.0", "url": "https://www.apache.org/licenses/LICENSE-2.0" }, - "version": "1.0.0" + "version": "1.0.1" }, "paths": { "/": { @@ -846,4 +846,4 @@ "description": "Hugging Face Text Generation Inference API" } ] -} \ No newline at end of file +} diff --git a/docs/source/basic_tutorials/gated_model_access.md b/docs/source/basic_tutorials/gated_model_access.md index 5d8e98f4..08c76de2 100644 --- a/docs/source/basic_tutorials/gated_model_access.md +++ b/docs/source/basic_tutorials/gated_model_access.md @@ -19,6 +19,6 @@ docker run --gpus all \ --shm-size 1g \ -e HUGGING_FACE_HUB_TOKEN=$token \ -p 8080:80 \ - -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.0 \ + -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.1 \ --model-id $model -``` \ No newline at end of file +``` diff --git a/docs/source/quicktour.md b/docs/source/quicktour.md index f447bc19..5b37c03f 100644 --- a/docs/source/quicktour.md +++ b/docs/source/quicktour.md @@ -8,7 +8,7 @@ Let's say you want to deploy [Falcon-7B Instruct](https://huggingface.co/tiiuae/ model=tiiuae/falcon-7b-instruct volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run -docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.0 --model-id $model +docker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.0.1 --model-id $model ``` diff --git a/server/.gitignore b/server/.gitignore index aef74bb4..2e1db124 100644 --- a/server/.gitignore +++ b/server/.gitignore @@ -155,4 +155,7 @@ dmypy.json cython_debug/ transformers -safetensors \ No newline at end of file +safetensors +flash-attention/ +flash-attention-v2/ +vllm/ diff --git a/server/pyproject.toml b/server/pyproject.toml index 25ffc538..8eeae616 100644 --- a/server/pyproject.toml +++ b/server/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "text-generation-server" -version = "1.0.0" +version = "1.0.1" description = "Text Generation Inference Python gRPC Server" authors = ["Olivier Dehaene "]