Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fixing the dockerfile warnings. (#2173)

This commit is contained in:
Nicolas Patry 2024-07-03 12:48:45 +02:00 committed by GitHub
parent be4a4c47f9
commit 2b3bd1e008
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 28 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
Dockerfile
View File

@ -4,7 +4,7 @@ WORKDIR /usr/src
ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse
FROM chef as planner FROM chef AS planner
COPY Cargo.lock Cargo.lock COPY Cargo.lock Cargo.lock
COPY Cargo.toml Cargo.toml COPY Cargo.toml Cargo.toml
COPY rust-toolchain.toml rust-toolchain.toml COPY rust-toolchain.toml rust-toolchain.toml
@ -38,7 +38,7 @@ RUN cargo build --profile release-opt
# Python builder # Python builder
# Adapted from: https://github.com/pytorch/pytorch/blob/master/Dockerfile # Adapted from: https://github.com/pytorch/pytorch/blob/master/Dockerfile
FROM nvidia/cuda:12.1.0-devel-ubuntu22.04 as pytorch-install FROM nvidia/cuda:12.1.0-devel-ubuntu22.04 AS pytorch-install
ARG PYTORCH_VERSION=2.3.0 ARG PYTORCH_VERSION=2.3.0
ARG PYTHON_VERSION=3.10 ARG PYTHON_VERSION=3.10
@ -81,7 +81,7 @@ RUN case ${TARGETPLATFORM} in \
/opt/conda/bin/conda clean -ya /opt/conda/bin/conda clean -ya
# CUDA kernels builder image # CUDA kernels builder image
FROM pytorch-install as kernel-builder FROM pytorch-install AS kernel-builder
ARG MAX_JOBS=8 ARG MAX_JOBS=8
@ -90,7 +90,7 @@ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-ins
&& rm -rf /var/lib/apt/lists/* && rm -rf /var/lib/apt/lists/*
# Build Flash Attention CUDA kernels # Build Flash Attention CUDA kernels
FROM kernel-builder as flash-att-builder FROM kernel-builder AS flash-att-builder
WORKDIR /usr/src WORKDIR /usr/src
@ -100,7 +100,7 @@ COPY server/Makefile-flash-att Makefile
RUN make build-flash-attention RUN make build-flash-attention
# Build Flash Attention v2 CUDA kernels # Build Flash Attention v2 CUDA kernels
FROM kernel-builder as flash-att-v2-builder FROM kernel-builder AS flash-att-v2-builder
WORKDIR /usr/src WORKDIR /usr/src
@ -110,14 +110,14 @@ COPY server/Makefile-flash-att-v2 Makefile
RUN make build-flash-attention-v2-cuda RUN make build-flash-attention-v2-cuda
# Build Transformers exllama kernels # Build Transformers exllama kernels
FROM kernel-builder as exllama-kernels-builder FROM kernel-builder AS exllama-kernels-builder
WORKDIR /usr/src WORKDIR /usr/src
COPY server/exllama_kernels/ . COPY server/exllama_kernels/ .
RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" python setup.py build RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" python setup.py build
# Build Transformers exllama kernels # Build Transformers exllama kernels
FROM kernel-builder as exllamav2-kernels-builder FROM kernel-builder AS exllamav2-kernels-builder
WORKDIR /usr/src WORKDIR /usr/src
COPY server/exllamav2_kernels/ . COPY server/exllamav2_kernels/ .
@ -125,42 +125,42 @@ COPY server/exllamav2_kernels/ .
RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" python setup.py build RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" python setup.py build
# Build Transformers awq kernels # Build Transformers awq kernels
FROM kernel-builder as awq-kernels-builder FROM kernel-builder AS awq-kernels-builder
WORKDIR /usr/src WORKDIR /usr/src
COPY server/Makefile-awq Makefile COPY server/Makefile-awq Makefile
# Build specific version of transformers # Build specific version of transformers
RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" make build-awq RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" make build-awq
# Build eetq kernels # Build eetq kernels
FROM kernel-builder as eetq-kernels-builder FROM kernel-builder AS eetq-kernels-builder
WORKDIR /usr/src WORKDIR /usr/src
COPY server/Makefile-eetq Makefile COPY server/Makefile-eetq Makefile
# Build specific version of transformers # Build specific version of transformers
RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" make build-eetq RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" make build-eetq
# Build marlin kernels # Build marlin kernels
FROM kernel-builder as marlin-kernels-builder FROM kernel-builder AS marlin-kernels-builder
WORKDIR /usr/src WORKDIR /usr/src
COPY server/marlin/ . COPY server/marlin/ .
# Build specific version of transformers # Build specific version of transformers
RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" python setup.py build RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" python setup.py build
# Build Lorax Punica kernels # Build Lorax Punica kernels
FROM kernel-builder as lorax-punica-builder FROM kernel-builder AS lorax-punica-builder
WORKDIR /usr/src WORKDIR /usr/src
COPY server/Makefile-lorax-punica Makefile COPY server/Makefile-lorax-punica Makefile
# Build specific version of transformers # Build specific version of transformers
RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" make build-lorax-punica RUN TORCH_CUDA_ARCH_LIST="8.0;8.6+PTX" make build-lorax-punica
# Build Transformers CUDA kernels # Build Transformers CUDA kernels
FROM kernel-builder as custom-kernels-builder FROM kernel-builder AS custom-kernels-builder
WORKDIR /usr/src WORKDIR /usr/src
COPY server/custom_kernels/ . COPY server/custom_kernels/ .
# Build specific version of transformers # Build specific version of transformers
RUN python setup.py build RUN python setup.py build
# Build vllm CUDA kernels # Build vllm CUDA kernels
FROM kernel-builder as vllm-builder FROM kernel-builder AS vllm-builder
WORKDIR /usr/src WORKDIR /usr/src
@ -172,13 +172,13 @@ COPY server/Makefile-vllm Makefile
RUN make build-vllm-cuda RUN make build-vllm-cuda
# Build mamba kernels # Build mamba kernels
FROM kernel-builder as mamba-builder FROM kernel-builder AS mamba-builder
WORKDIR /usr/src WORKDIR /usr/src
COPY server/Makefile-selective-scan Makefile COPY server/Makefile-selective-scan Makefile
RUN make build-all RUN make build-all
# Text Generation Inference base image # Text Generation Inference base image
FROM nvidia/cuda:12.1.0-base-ubuntu22.04 as base FROM nvidia/cuda:12.1.0-base-ubuntu22.04 AS base
# Conda env # Conda env
ENV PATH=/opt/conda/bin:$PATH \ ENV PATH=/opt/conda/bin:$PATH \
@ -260,7 +260,7 @@ COPY --from=builder /usr/src/target/release-opt/text-generation-launcher /usr/lo
# AWS Sagemaker compatible image # AWS Sagemaker compatible image
FROM base as sagemaker FROM base AS sagemaker
COPY sagemaker-entrypoint.sh entrypoint.sh COPY sagemaker-entrypoint.sh entrypoint.sh
RUN chmod +x entrypoint.sh RUN chmod +x entrypoint.sh

16
Dockerfile_amd
View File

@ -4,7 +4,7 @@ WORKDIR /usr/src
ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse
FROM chef as planner FROM chef AS planner
COPY Cargo.lock Cargo.lock COPY Cargo.lock Cargo.lock
COPY Cargo.toml Cargo.toml COPY Cargo.toml Cargo.toml
COPY rust-toolchain.toml rust-toolchain.toml COPY rust-toolchain.toml rust-toolchain.toml
@ -37,7 +37,7 @@ COPY launcher launcher
RUN cargo build --profile release-opt RUN cargo build --profile release-opt
# Text Generation Inference base image for RoCm # Text Generation Inference base image for RoCm
FROM rocm/dev-ubuntu-22.04:6.1.1_hip_update as base FROM rocm/dev-ubuntu-22.04:6.1.1_hip_update AS base
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
build-essential \ build-essential \
@ -115,7 +115,7 @@ ARG BUILD_CAFFE2="0" \
RUN cd pytorch && python tools/amd_build/build_amd.py && python setup.py install RUN cd pytorch && python tools/amd_build/build_amd.py && python setup.py install
# Set as recommended: https://github.com/ROCm/triton/wiki/A-script-to-set-program-execution-environment-in-ROCm # Set AS recommended: https://github.com/ROCm/triton/wiki/A-script-to-set-program-execution-environment-in-ROCm
ENV HIP_FORCE_DEV_KERNARG=1 ENV HIP_FORCE_DEV_KERNARG=1
# On MI250 and MI300, performances for flash with Triton FA are slightly better than CK. # On MI250 and MI300, performances for flash with Triton FA are slightly better than CK.
@ -143,26 +143,26 @@ COPY server/Makefile-flash-att-v2 Makefile
RUN make build-flash-attention-v2-rocm RUN make build-flash-attention-v2-rocm
# Build Transformers CUDA kernels (gpt-neox and bloom) # Build Transformers CUDA kernels (gpt-neox and bloom)
FROM kernel-builder as custom-kernels-builder FROM kernel-builder AS custom-kernels-builder
WORKDIR /usr/src WORKDIR /usr/src
COPY server/custom_kernels/ . COPY server/custom_kernels/ .
RUN python setup.py build RUN python setup.py build
# Build exllama kernels # Build exllama kernels
FROM kernel-builder as exllama-kernels-builder FROM kernel-builder AS exllama-kernels-builder
WORKDIR /usr/src WORKDIR /usr/src
COPY server/exllama_kernels/ . COPY server/exllama_kernels/ .
RUN python setup.py build RUN python setup.py build
# Build exllama v2 kernels # Build exllama v2 kernels
FROM kernel-builder as exllamav2-kernels-builder FROM kernel-builder AS exllamav2-kernels-builder
WORKDIR /usr/src WORKDIR /usr/src
COPY server/exllamav2_kernels/ . COPY server/exllamav2_kernels/ .
RUN python setup.py build RUN python setup.py build
FROM base as base-copy FROM base AS base-copy
# Text Generation Inference base env # Text Generation Inference base env
ENV HUGGINGFACE_HUB_CACHE=/data \ ENV HUGGINGFACE_HUB_CACHE=/data \
@ -201,7 +201,7 @@ 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 COPY --from=builder /usr/src/target/release-opt/text-generation-launcher /usr/local/bin/text-generation-launcher
# AWS Sagemaker compatible image # AWS Sagemaker compatible image
FROM base as sagemaker FROM base AS sagemaker
COPY sagemaker-entrypoint.sh entrypoint.sh COPY sagemaker-entrypoint.sh entrypoint.sh
RUN chmod +x entrypoint.sh RUN chmod +x entrypoint.sh

8
Dockerfile_intel
View File

@ -5,7 +5,7 @@ WORKDIR /usr/src
ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse ARG CARGO_REGISTRIES_CRATES_IO_PROTOCOL=sparse
FROM chef as planner FROM chef AS planner
COPY Cargo.lock Cargo.lock COPY Cargo.lock Cargo.lock
COPY Cargo.toml Cargo.toml COPY Cargo.toml Cargo.toml
COPY rust-toolchain.toml rust-toolchain.toml COPY rust-toolchain.toml rust-toolchain.toml
@ -40,7 +40,7 @@ RUN cargo build --profile release-opt
# Text Generation Inference base image for Intel # Text Generation Inference base image for Intel
FROM intel/intel-extension-for-pytorch:2.1.30-xpu as xpu FROM intel/intel-extension-for-pytorch:2.1.30-xpu AS xpu
USER root USER root
# libssl.so.1.1 is not installed on Ubuntu 22.04 by default, install it # libssl.so.1.1 is not installed on Ubuntu 22.04 by default, install it
@ -95,7 +95,7 @@ COPY --from=builder /usr/src/target/release-opt/text-generation-launcher /usr/lo
# Text Generation Inference base image for Intel-cpu # Text Generation Inference base image for Intel-cpu
FROM ubuntu:22.04 as cpu FROM ubuntu:22.04 AS cpu
RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \ RUN apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y --no-install-recommends \
curl \ curl \
@ -172,6 +172,6 @@ COPY --from=builder /usr/src/target/release-opt/text-generation-router /usr/loca
# Install launcher # Install launcher
COPY --from=builder /usr/src/target/release-opt/text-generation-launcher /usr/local/bin/text-generation-launcher COPY --from=builder /usr/src/target/release-opt/text-generation-launcher /usr/local/bin/text-generation-launcher
FROM ${PLATFORM} as final FROM ${PLATFORM} AS final
ENTRYPOINT ["text-generation-launcher"] ENTRYPOINT ["text-generation-launcher"]
CMD ["--json-output"] CMD ["--json-output"]