88 lines
2.6 KiB
Docker
88 lines
2.6 KiB
Docker
################### vLLM Base Dockerfile ###################
|
|
# This Dockerfile is for building the image that the
|
|
# vLLM worker container will use as its base image.
|
|
# If your changes are outside of the vLLM source code, you
|
|
# do not need to build this image.
|
|
##########################################################
|
|
|
|
# Define the CUDA version for the build
|
|
ARG WORKER_CUDA_VERSION=11.8.0
|
|
|
|
FROM nvidia/cuda:${WORKER_CUDA_VERSION}-devel-ubuntu22.04 AS dev
|
|
|
|
# Re-declare ARG after FROM
|
|
ARG WORKER_CUDA_VERSION
|
|
|
|
# Update and install dependencies
|
|
RUN apt-get update -y \
|
|
&& apt-get install -y python3-pip git
|
|
|
|
# Set working directory
|
|
WORKDIR /vllm-installation
|
|
|
|
# Install build and runtime dependencies
|
|
COPY vllm/requirements-${WORKER_CUDA_VERSION}.txt requirements.txt
|
|
RUN --mount=type=cache,target=/root/.cache/pip \
|
|
pip install -r requirements.txt
|
|
|
|
# Install development dependencies
|
|
COPY vllm/requirements-dev.txt requirements-dev.txt
|
|
RUN --mount=type=cache,target=/root/.cache/pip \
|
|
pip install -r requirements-dev.txt
|
|
|
|
FROM dev AS build
|
|
|
|
# Re-declare ARG after FROM
|
|
ARG WORKER_CUDA_VERSION
|
|
|
|
# Install build dependencies
|
|
COPY vllm/requirements-build.txt requirements-build.txt
|
|
RUN --mount=type=cache,target=/root/.cache/pip \
|
|
pip install -r requirements-build.txt
|
|
|
|
# Copy necessary files
|
|
COPY vllm/csrc csrc
|
|
COPY vllm/setup.py setup.py
|
|
COPY vllm/pyproject.toml pyproject.toml
|
|
COPY vllm/vllm/__init__.py vllm/__init__.py
|
|
|
|
# Set environment variables for building extensions
|
|
ARG torch_cuda_arch_list='7.0 7.5 8.0 8.6 8.9 9.0+PTX'
|
|
ENV TORCH_CUDA_ARCH_LIST=${torch_cuda_arch_list}
|
|
ARG max_jobs=48
|
|
ENV MAX_JOBS=${max_jobs}
|
|
ARG nvcc_threads=1024
|
|
ENV NVCC_THREADS=${nvcc_threads}
|
|
ENV WORKER_CUDA_VERSION=${WORKER_CUDA_VERSION}
|
|
ENV VLLM_INSTALL_PUNICA_KERNELS=0
|
|
# Build extensions
|
|
RUN ldconfig /usr/local/cuda-$(echo "$WORKER_CUDA_VERSION" | sed 's/\.0$//')/compat/
|
|
RUN python3 setup.py build_ext --inplace
|
|
|
|
FROM nvidia/cuda:${WORKER_CUDA_VERSION}-runtime-ubuntu22.04 AS vllm-base
|
|
|
|
# Re-declare ARG after FROM
|
|
ARG WORKER_CUDA_VERSION
|
|
|
|
# Update and install necessary libraries
|
|
RUN apt-get update -y \
|
|
&& apt-get install -y python3-pip
|
|
|
|
# Set working directory
|
|
WORKDIR /vllm-installation
|
|
|
|
|
|
# Install runtime dependencies
|
|
COPY vllm/requirements-${WORKER_CUDA_VERSION}.txt requirements.txt
|
|
RUN --mount=type=cache,target=/root/.cache/pip \
|
|
pip install -r requirements.txt
|
|
|
|
# Copy built files from the build stage
|
|
COPY --from=build /vllm-installation/vllm/*.so /vllm-installation/vllm/
|
|
COPY vllm/vllm vllm
|
|
|
|
# Set PYTHONPATH environment variable
|
|
ENV PYTHONPATH="/"
|
|
|
|
# Validate the installation
|
|
RUN python3 -c "import sys; print(sys.path); import vllm; print(vllm.__file__)" |