biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI/Build][Docker] Add centralized version manifest for Docker builds (#31492)

Browse Source 
Signed-off-by: Mritunjay Sharma <mritunjay.sharma@chainguard.dev>
This commit is contained in:
Mritunjay Kumar Sharma
2026-01-17 19:15:30 +05:30
committed by GitHub
parent 2b99f210f5
commit 9e078d0582
4 changed files with 271 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
docker/Dockerfile
View File

@@ -5,6 +5,23 @@
# docs/contributing/dockerfile/dockerfile.md and
# docs/assets/contributing/dockerfile-stages-dependency.png
# =============================================================================
# VERSION MANAGEMENT
# =============================================================================
# ARG defaults in this Dockerfile are the source of truth for pinned versions.
# docker/versions.json is auto-generated for use with docker buildx bake.
#
# When updating versions:
# 1. Edit the ARG defaults below
# 2. Run: python tools/generate_versions_json.py
#
# To query versions programmatically:
# jq -r '.variable.CUDA_VERSION.default' docker/versions.json
#
# To build with bake:
# docker buildx bake -f docker/docker-bake.hcl -f docker/versions.json
# =============================================================================
ARG CUDA_VERSION=12.9.1
ARG PYTHON_VERSION=3.12
@@ -141,6 +158,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
# CUDA arch list used by torch
# Explicitly set the list to avoid issues with torch 2.2
# See https://github.com/pytorch/pytorch/pull/123243
# From versions.json: .torch.cuda_arch_list
ARG torch_cuda_arch_list='7.0 7.5 8.0 8.9 9.0 10.0 12.0'
ENV TORCH_CUDA_ARCH_LIST=${torch_cuda_arch_list}
#################### BUILD BASE IMAGE ####################
@@ -256,7 +274,8 @@ ENV UV_LINK_MODE=copy
WORKDIR /workspace
# Build DeepGEMM wheel
ARG DEEPGEMM_GIT_REF
# Default moved here from tools/install_deepgemm.sh for centralized version management
ARG DEEPGEMM_GIT_REF=594953acce41793ae00a1233eb516044d604bcb6
COPY tools/install_deepgemm.sh /tmp/install_deepgemm.sh
RUN --mount=type=cache,target=/root/.cache/uv \
mkdir -p /tmp/deepgemm/dist && \
@@ -271,8 +290,9 @@ RUN mkdir -p /tmp/deepgemm/dist && touch /tmp/deepgemm/dist/.deepgemm_skipped
# Build pplx-kernels and DeepEP wheels
COPY tools/ep_kernels/install_python_libraries.sh /tmp/install_python_libraries.sh
ARG PPLX_COMMIT_HASH
ARG DEEPEP_COMMIT_HASH
# Defaults moved here from tools/ep_kernels/install_python_libraries.sh for centralized version management
ARG PPLX_COMMIT_HASH=12cecfd
ARG DEEPEP_COMMIT_HASH=73b6ea4
ARG NVSHMEM_VER
RUN --mount=type=cache,target=/root/.cache/uv \
mkdir -p /tmp/ep_kernels_workspace/dist && \
@@ -474,6 +494,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
# Install FlashInfer pre-compiled kernel cache and binaries
# This is ~1.1GB and only changes when FlashInfer version bumps
# https://docs.flashinfer.ai/installation.html
# From versions.json: .flashinfer.version
ARG FLASHINFER_VERSION=0.5.3
RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --system flashinfer-cubin==${FLASHINFER_VERSION} \
@@ -503,14 +524,20 @@ RUN set -eux; \
# Install vllm-openai dependencies (saves ~2.6s per build)
# These are stable packages that don't depend on vLLM itself
# From versions.json: .bitsandbytes.x86_64, .bitsandbytes.arm64
# From versions.json: .openai_server_extras.timm, .openai_server_extras.runai_model_streamer
ARG BITSANDBYTES_VERSION_X86=0.46.1
ARG BITSANDBYTES_VERSION_ARM64=0.42.0
ARG TIMM_VERSION=">=1.0.17"
ARG RUNAI_MODEL_STREAMER_VERSION=">=0.15.3"
RUN --mount=type=cache,target=/root/.cache/uv \
if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
BITSANDBYTES_VERSION="0.42.0"; \
BITSANDBYTES_VERSION="${BITSANDBYTES_VERSION_ARM64}"; \
else \
BITSANDBYTES_VERSION="0.46.1"; \
BITSANDBYTES_VERSION="${BITSANDBYTES_VERSION_X86}"; \
fi; \
uv pip install --system accelerate hf_transfer modelscope \
"bitsandbytes>=${BITSANDBYTES_VERSION}" 'timm>=1.0.17' 'runai-model-streamer[s3,gcs]>=0.15.3'
"bitsandbytes>=${BITSANDBYTES_VERSION}" "timm${TIMM_VERSION}" "runai-model-streamer[s3,gcs]${RUNAI_MODEL_STREAMER_VERSION}"
# ============================================================
# VLLM INSTALLATION (depends on build stage)