diff --git a/docker/Dockerfile.cpu b/docker/Dockerfile.cpu index 827ef736b0..3afcc21308 100644 --- a/docker/Dockerfile.cpu +++ b/docker/Dockerfile.cpu @@ -9,7 +9,6 @@ # # Build targets: # vllm-openai (default): used for serving deployment -# vllm-openai-zen: vLLM from source + zentorch from PyPI via vllm[zen] # vllm-test: used for CI tests # vllm-dev: used for development # @@ -469,19 +468,3 @@ LABEL ai.vllm.build.python-version="${PYTHON_VERSION:-3.12}" COPY examples examples ENTRYPOINT ["vllm", "serve"] - - -######################### ZEN CPU PYPI IMAGE ######################### -FROM vllm-openai AS vllm-openai-zen - -ARG TARGETARCH - -RUN if [ "$TARGETARCH" != "amd64" ]; then \ - echo "ERROR: vllm-openai-amd only supports --platform=linux/amd64"; \ - exit 1; \ - fi - -RUN --mount=type=cache,target=/root/.cache/uv \ - uv pip install "vllm[zen]" - -ENTRYPOINT ["vllm", "serve"] diff --git a/docker/Dockerfile.zen b/docker/Dockerfile.zen new file mode 100644 index 0000000000..8c9e49c5f8 --- /dev/null +++ b/docker/Dockerfile.zen @@ -0,0 +1,98 @@ +# SPDX-License-Identifier: Apache-2.0 +# SPDX-FileCopyrightText: Copyright contributors to the vLLM project + +# This Dockerfile builds AMD Zen CPU images for vLLM with zentorch. +# It layers on top of the CPU image produced by docker/Dockerfile.cpu. +# +# Supported platforms: +# - linux/amd64 (Zen2 and newer; Zen5 is the canonical CI target) +# +# Build targets: +# vllm-openai-zen (default): vLLM + zentorch for serving +# vllm-zen-test : vllm-openai-zen + test deps for CI +# +# Build workflow (see .buildkite/image_build/image_build_zen_cpu.sh): +# 1. Obtain a CPU base image that already has vLLM installed. In CI this is the +# shared `:-cpu` image (docker/Dockerfile.cpu --target +# vllm-test); either the vllm-test or vllm-openai target works as the base +# since both install vLLM into the same venv this stage extends. +# 2. docker build -f docker/Dockerfile.zen --build-arg BASE_IMAGE=: \ +# --target vllm-zen-test -t : . + +ARG BASE_IMAGE +ARG PYTHON_VERSION=3.12 +ARG ZENTORCH_VERSION + +######################### ZEN OPENAI IMAGE ######################### +FROM ${BASE_IMAGE} AS vllm-openai-zen + +ARG TARGETARCH +ARG ZENTORCH_VERSION + +RUN if [ "${TARGETARCH}" != "amd64" ]; then \ + echo "ERROR: Dockerfile.zen requires --platform=linux/amd64"; \ + exit 1; \ + fi + +WORKDIR /vllm-workspace + +RUN --mount=type=cache,target=/root/.cache/uv \ + if [ -n "${ZENTORCH_VERSION}" ]; then \ + uv pip install "zentorch==${ZENTORCH_VERSION}"; \ + else \ + uv pip install "vllm[zen]"; \ + fi + +LABEL org.opencontainers.image.title="vLLM Zen CPU" +LABEL org.opencontainers.image.description="vLLM with zentorch for AMD Zen CPUs" +LABEL org.opencontainers.image.vendor="vLLM Project" +LABEL org.opencontainers.image.source="https://github.com/vllm-project/vllm" +LABEL ai.vllm.build.target-arch="${TARGETARCH}" +LABEL ai.vllm.build.python-version="${PYTHON_VERSION}" +LABEL ai.vllm.build.zentorch-version="${ZENTORCH_VERSION:-unpinned}" + +ENTRYPOINT ["vllm", "serve"] + +######################### ZEN TEST IMAGE ######################### +FROM vllm-openai-zen AS vllm-zen-test + +WORKDIR /vllm-workspace + +COPY requirements/common.txt requirements/common.txt +COPY requirements/test/cuda.in requirements/test/zen.in + +RUN sed -i '/mamba_ssm/d' requirements/test/zen.in && \ + sed -i 's/^torch==.*/torch==2.13.0/g' requirements/test/zen.in && \ + sed -i 's/torchaudio.*/torchaudio/g' requirements/test/zen.in && \ + sed -i 's/torchvision.*/torchvision/g' requirements/test/zen.in && \ + # zentorch parity: keep sentence-transformers pinned where vllm-test-deps did. + sed -i 's/^sentence-transformers.*/sentence-transformers==5.3.0/g' requirements/test/zen.in && \ + uv pip compile requirements/test/zen.in \ + -o requirements/test/zen.txt \ + --index-strategy unsafe-best-match --torch-backend cpu + +RUN --mount=type=cache,target=/root/.cache/uv \ + uv pip install -r requirements/test/zen.txt --torch-backend cpu + +# Reassert zentorch's torch in case test-deps moved it. +RUN --mount=type=cache,target=/root/.cache/uv \ + if [ -n "${ZENTORCH_VERSION}" ]; then \ + uv pip install --force-reinstall --no-deps "zentorch==${ZENTORCH_VERSION}"; \ + else \ + uv pip install --force-reinstall --no-deps "vllm[zen]"; \ + fi + +ADD ./tests/ ./tests/ +ADD ./examples/ ./examples/ +ADD ./benchmarks/ ./benchmarks/ +ADD ./vllm/collect_env.py . +ADD ./docker/ ./docker/ +ADD ./.buildkite/ ./.buildkite/ + +RUN --mount=type=cache,target=/root/.cache/uv \ + uv pip install -e tests/vllm_test_utils + +ENV HF_XET_HIGH_PERFORMANCE=1 +ENV HF_HUB_DOWNLOAD_TIMEOUT=60 + +ENTRYPOINT [] \ No newline at end of file