hf_text-generation-inference/Dockerfile

205 lines
6.2 KiB
Docker
Raw Normal View History

# Rust builder
2023-07-01 11:25:41 -06:00
FROM lukemathwalker/cargo-chef:latest-rust-1.70 AS chef
2023-03-03 07:07:27 -07:00
WORKDIR /usr/src
ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse
2023-03-03 07:07:27 -07:00
FROM chef as planner
COPY Cargo.toml Cargo.toml
COPY rust-toolchain.toml rust-toolchain.toml
COPY proto proto
2023-05-09 06:39:59 -06:00
COPY benchmark benchmark
2023-03-03 07:07:27 -07:00
COPY router router
COPY launcher launcher
RUN cargo chef prepare --recipe-path recipe.json
FROM chef AS builder
2023-02-13 05:02:45 -07:00
ARG GIT_SHA
2023-05-02 07:43:19 -06:00
ARG DOCKER_LABEL
2023-02-13 05:02:45 -07:00
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 $PROTOC_ZIP
2022-10-14 07:56:21 -06:00
2023-03-03 07:07:27 -07:00
COPY --from=planner /usr/src/recipe.json recipe.json
RUN cargo chef cook --release --recipe-path recipe.json
2022-10-14 07:56:21 -06:00
2023-03-03 07:07:27 -07:00
COPY Cargo.toml Cargo.toml
COPY rust-toolchain.toml rust-toolchain.toml
2022-10-14 07:56:21 -06:00
COPY proto proto
2023-05-09 06:39:59 -06:00
COPY benchmark benchmark
2022-10-14 07:56:21 -06:00
COPY router router
2022-10-18 07:19:03 -06:00
COPY launcher launcher
2023-03-03 07:07:27 -07:00
RUN cargo build --release
2022-10-18 07:19:03 -06:00
# Python builder
# Adapted from: https://github.com/pytorch/pytorch/blob/master/Dockerfile
FROM debian:bullseye-slim as pytorch-install
ARG PYTORCH_VERSION=2.0.0
ARG PYTHON_VERSION=3.9
ARG CUDA_VERSION=11.8
ARG MAMBA_VERSION=23.1.0-1
ARG CUDA_CHANNEL=nvidia
ARG INSTALL_CHANNEL=pytorch
# Automatically set by buildx
ARG TARGETPLATFORM
ENV PATH /opt/conda/bin:$PATH
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
build-essential \
ca-certificates \
ccache \
curl \
git && \
rm -rf /var/lib/apt/lists/*
# Install conda
# translating Docker's TARGETPLATFORM into mamba arches
RUN case ${TARGETPLATFORM} in \
"linux/arm64") MAMBA_ARCH=aarch64 ;; \
*) MAMBA_ARCH=x86_64 ;; \
esac && \
curl -fsSL -v -o ~/mambaforge.sh -O "https://github.com/conda-forge/miniforge/releases/download/${MAMBA_VERSION}/Mambaforge-${MAMBA_VERSION}-Linux-${MAMBA_ARCH}.sh"
RUN chmod +x ~/mambaforge.sh && \
bash ~/mambaforge.sh -b -p /opt/conda && \
rm ~/mambaforge.sh
# Install pytorch
# On arm64 we exit with an error code
RUN case ${TARGETPLATFORM} in \
"linux/arm64") exit 1 ;; \
*) /opt/conda/bin/conda update -y conda && \
/opt/conda/bin/conda install -c "${INSTALL_CHANNEL}" -c "${CUDA_CHANNEL}" -y "python=${PYTHON_VERSION}" pytorch==$PYTORCH_VERSION "pytorch-cuda=$(echo $CUDA_VERSION | cut -d'.' -f 1-2)" ;; \
esac && \
/opt/conda/bin/conda clean -ya
# CUDA kernels builder image
FROM pytorch-install as kernel-builder
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
ninja-build \
&& rm -rf /var/lib/apt/lists/*
RUN /opt/conda/bin/conda install -c "nvidia/label/cuda-11.8.0" cuda==11.8 && \
/opt/conda/bin/conda clean -ya
# Build Flash Attention CUDA kernels
FROM kernel-builder as flash-att-builder
WORKDIR /usr/src
COPY server/Makefile-flash-att Makefile
# Build specific version of flash attention
RUN make build-flash-attention
# Build Flash Attention v2 CUDA kernels
FROM kernel-builder as flash-att-v2-builder
WORKDIR /usr/src
COPY server/Makefile-flash-att-v2 Makefile
# Build specific version of flash attention v2
RUN make build-flash-attention-v2
# Build Transformers CUDA kernels
FROM kernel-builder as custom-kernels-builder
WORKDIR /usr/src
COPY server/custom_kernels/ .
# Build specific version of transformers
RUN python setup.py build
# Build vllm CUDA kernels
FROM kernel-builder as vllm-builder
WORKDIR /usr/src
COPY server/Makefile-vllm Makefile
# Build specific version of vllm
RUN make build-vllm
# Text Generation Inference base image
2023-05-12 10:38:59 -06:00
FROM nvidia/cuda:11.8.0-base-ubuntu20.04 as base
# Conda env
ENV PATH=/opt/conda/bin:$PATH \
CONDA_PREFIX=/opt/conda
# Text Generation Inference base env
ENV HUGGINGFACE_HUB_CACHE=/data \
2023-02-18 06:04:11 -07:00
HF_HUB_ENABLE_HF_TRANSFER=1 \
PORT=80
2022-10-14 07:56:21 -06:00
WORKDIR /usr/src
2023-03-24 07:02:14 -06:00
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
libssl-dev \
ca-certificates \
make \
&& rm -rf /var/lib/apt/lists/*
2022-10-14 07:56:21 -06:00
# Copy conda with PyTorch installed
COPY --from=pytorch-install /opt/conda /opt/conda
2022-10-14 07:56:21 -06:00
# Copy build artifacts from flash attention builder
COPY --from=flash-att-builder /usr/src/flash-attention/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
COPY --from=flash-att-builder /usr/src/flash-attention/csrc/layer_norm/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
COPY --from=flash-att-builder /usr/src/flash-attention/csrc/rotary/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
# Copy build artifacts from flash attention v2 builder
COPY --from=flash-att-v2-builder /usr/src/flash-attention-v2/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
# Copy build artifacts from custom kernels builder
COPY --from=custom-kernels-builder /usr/src/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
# Copy builds artifacts from vllm builder
COPY --from=vllm-builder /usr/src/vllm/build/lib.linux-x86_64-cpython-39 /opt/conda/lib/python3.9/site-packages
# Install flash-attention dependencies
RUN pip install einops --no-cache-dir
2022-10-14 07:56:21 -06:00
# Install server
COPY proto proto
2022-10-14 07:56:21 -06:00
COPY server server
COPY server/Makefile server/Makefile
2022-10-14 07:56:21 -06:00
RUN cd server && \
make gen-server && \
pip install -r requirements.txt && \
pip install ".[bnb, accelerate]" --no-cache-dir
2022-10-14 07:56:21 -06:00
# Install benchmarker
COPY --from=builder /usr/src/target/release/text-generation-benchmark /usr/local/bin/text-generation-benchmark
2022-10-14 07:56:21 -06:00
# Install router
2023-03-03 07:07:27 -07:00
COPY --from=builder /usr/src/target/release/text-generation-router /usr/local/bin/text-generation-router
# Install launcher
2023-03-03 07:07:27 -07:00
COPY --from=builder /usr/src/target/release/text-generation-launcher /usr/local/bin/text-generation-launcher
2022-10-14 07:56:21 -06:00
feat(server): Add inference support for GPTQ (llama + falcon tested) + Quantization script (#438) Let's start discussing implementation. - Need to expose the quantization scripts (either included here or add doc on how to use https://github.com/qwopqwop200/GPTQ-for-LLaMa) - Make sure GPTQ works for multiple models (priority to Falcon). Currently it means that every place we use `get_{tensor|sharded}` to check for quantization. My idea is to reintegrate as much as possible into `utils/layer.py` by expanding `load_multi` to be a bit more generic. This might require some thinking, but ultimately the `qweight,qzeros,scales,g_idx` should be in a single place, and independant of bias presence. # What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflects the extent of your awesome contribution. Then, please replace this with a description of the change and which issue is fixed (if applicable). Please also include relevant motivation and context. List any dependencies (if any) that are required for this change. Once you're done, someone will review your PR shortly (see the section "Who can review?" below to tag some potential reviewers). They may suggest changes to make the code even better. If no one reviewed your PR after a week has passed, don't hesitate to post a new comment @-mentioning the same persons---sometimes notifications get lost. --> <!-- Remove if not applicable --> 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. <!-- Your PR will be replied to more quickly if you can figure out the right person to tag with @ @OlivierDehaene OR @Narsil --> --------- Co-authored-by: Ubuntu <ubuntu@ip-172-31-41-161.ec2.internal> Co-authored-by: OlivierDehaene <olivier@huggingface.co>
2023-06-26 04:27:01 -06:00
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
build-essential \
g++ \
&& rm -rf /var/lib/apt/lists/*
# AWS Sagemaker compatbile image
FROM base as sagemaker
COPY sagemaker-entrypoint.sh entrypoint.sh
RUN chmod +x entrypoint.sh
ENTRYPOINT ["./entrypoint.sh"]
# Final image
FROM base
ENTRYPOINT ["text-generation-launcher"]
CMD ["--json-output"]