diff --git a/.buildkite/test-pipeline.yaml b/.buildkite/test-pipeline.yaml index 4890e070c11ed..84e016c8c6f08 100644 --- a/.buildkite/test-pipeline.yaml +++ b/.buildkite/test-pipeline.yaml @@ -21,7 +21,7 @@ steps: fast_check: true fast_check_only: true commands: - - apt-get install curl libsodium23 && pytest -v -s tensorizer_loader # Tensorizer + - apt-get install -y curl libsodium23 && pytest -v -s tensorizer_loader # Tensorizer - pytest -v -s metrics # Metrics - "pip install \ opentelemetry-sdk \ @@ -221,7 +221,7 @@ steps: - label: Tensorizer Test #mirror_hardwares: [amd] commands: - - apt-get install curl libsodium23 + - apt-get install -y curl libsodium23 - export VLLM_WORKER_MULTIPROC_METHOD=spawn - pytest -v -s tensorizer_loader diff --git a/Dockerfile b/Dockerfile index 89d9be0e84ddb..ff081b82ca0f0 100644 --- a/Dockerfile +++ b/Dockerfile @@ -8,10 +8,10 @@ ARG CUDA_VERSION=12.4.1 #################### BASE BUILD IMAGE #################### # prepare basic build environment -FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu22.04 AS base +FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu20.04 AS base ARG CUDA_VERSION=12.4.1 -ARG PYTHON_VERSION=3 +ARG PYTHON_VERSION=3.10 ENV DEBIAN_FRONTEND=noninteractive @@ -21,13 +21,16 @@ RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \ && apt-get install -y ccache software-properties-common \ && add-apt-repository ppa:deadsnakes/ppa \ && apt-get update -y \ - && apt-get install -y python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv python3-pip \ + && apt-get install -y python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv \ && if [ "${PYTHON_VERSION}" != "3" ]; then update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1; fi \ - && python3 --version \ - && python3 -m pip --version + && python3 --version RUN apt-get update -y \ - && apt-get install -y python3-pip git curl sudo + && apt-get install -y git curl sudo + +# Install pip s.t. it will be compatible with our PYTHON_VERSION +RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python${PYTHON_VERSION} +RUN python3 -m pip --version # Workaround for https://github.com/openai/triton/issues/2507 and # https://github.com/pytorch/pytorch/issues/107960 -- hopefully @@ -58,7 +61,7 @@ ENV TORCH_CUDA_ARCH_LIST=${torch_cuda_arch_list} #################### WHEEL BUILD IMAGE #################### FROM base AS build -ARG PYTHON_VERSION=3 +ARG PYTHON_VERSION=3.10 # install build dependencies COPY requirements-build.txt requirements-build.txt @@ -149,12 +152,27 @@ RUN pip --verbose wheel -r requirements-mamba.txt \ #################### vLLM installation IMAGE #################### # image with vLLM installed -FROM nvidia/cuda:${CUDA_VERSION}-base-ubuntu22.04 AS vllm-base +FROM nvidia/cuda:${CUDA_VERSION}-base-ubuntu20.04 AS vllm-base ARG CUDA_VERSION=12.4.1 +ARG PYTHON_VERSION=3.10 WORKDIR /vllm-workspace +RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \ + && echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections \ + && apt-get update -y \ + && apt-get install -y ccache software-properties-common \ + && add-apt-repository ppa:deadsnakes/ppa \ + && apt-get update -y \ + && apt-get install -y python${PYTHON_VERSION} python${PYTHON_VERSION}-dev python${PYTHON_VERSION}-venv \ + && if [ "${PYTHON_VERSION}" != "3" ]; then update-alternatives --install /usr/bin/python3 python3 /usr/bin/python${PYTHON_VERSION} 1; fi \ + && python3 --version + RUN apt-get update -y \ - && apt-get install -y python3-pip git vim + && apt-get install -y python3-pip git curl + +# Install pip s.t. it will be compatible with our PYTHON_VERSION +RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python${PYTHON_VERSION} +RUN python3 -m pip --version # Workaround for https://github.com/openai/triton/issues/2507 and # https://github.com/pytorch/pytorch/issues/107960 -- hopefully diff --git a/Dockerfile.openvino b/Dockerfile.openvino index 9861997b451a9..cfb786485266c 100644 --- a/Dockerfile.openvino +++ b/Dockerfile.openvino @@ -1,7 +1,7 @@ # The vLLM Dockerfile is used to construct vLLM image that can be directly used # to run the OpenAI compatible server. -FROM ubuntu:22.04 AS dev +FROM ubuntu:20.04 AS dev RUN apt-get update -y && \ apt-get install -y python3-pip git diff --git a/Dockerfile.xpu b/Dockerfile.xpu index c39e551672d20..f91baa11a3753 100644 --- a/Dockerfile.xpu +++ b/Dockerfile.xpu @@ -1,4 +1,4 @@ -FROM intel/oneapi-basekit:2024.1.0-devel-ubuntu22.04 +FROM intel/oneapi-basekit:2024.1.0-devel-ubuntu20.04 RUN wget -O- https://apt.repos.intel.com/intel-gpg-keys/GPG-PUB-KEY-INTEL-SW-PRODUCTS.PUB | gpg --dearmor | tee /usr/share/keyrings/intel-oneapi-archive-keyring.gpg > /dev/null && \ echo "deb [signed-by=/usr/share/keyrings/intel-oneapi-archive-keyring.gpg] https://apt.repos.intel.com/oneapi all main " | tee /etc/apt/sources.list.d/oneAPI.list && \