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

[release 2.11] Update to torch 2.11 (#34644)

Browse Source
This commit is contained in:
Andrey Talman
2026-04-07 21:55:48 -04:00
committed by GitHub
parent 5af684c319
commit 2111997f96
26 changed files with 112 additions and 86 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
docker/Dockerfile
View File

@@ -22,7 +22,7 @@
# docker buildx bake -f docker/docker-bake.hcl -f docker/versions.json
# =============================================================================
ARG CUDA_VERSION=12.9.1
ARG CUDA_VERSION=13.0.0
ARG PYTHON_VERSION=3.12
ARG UBUNTU_VERSION=22.04
@@ -37,7 +37,7 @@ ARG UBUNTU_VERSION=22.04
# compatibility with other Linux OSes. The main reason for this is that the
# glibc version is baked into the distro, and binaries built with one glibc
# version are not backwards compatible with OSes that use an earlier version.
ARG BUILD_BASE_IMAGE=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu20.04
ARG BUILD_BASE_IMAGE=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu22.04
# Using cuda base image with minimal dependencies necessary for JIT compilation (FlashInfer, DeepGEMM, EP kernels)
ARG FINAL_BASE_IMAGE=nvidia/cuda:${CUDA_VERSION}-base-ubuntu${UBUNTU_VERSION}
@@ -546,17 +546,21 @@ RUN apt-get update -y \
# Install CUDA development tools for runtime JIT compilation
# (FlashInfer, DeepGEMM, EP kernels all require compilation at runtime)
RUN CUDA_VERSION_DASH=$(echo $CUDA_VERSION | cut -d. -f1,2 | tr '.' '-') && \
CUDA_VERSION_SHORT=$(echo $CUDA_VERSION | cut -d. -f1,2) && \
apt-get update -y && \
apt-get install -y --no-install-recommends \
apt-get install -y --no-install-recommends --allow-change-held-packages \
cuda-nvcc-${CUDA_VERSION_DASH} \
cuda-cudart-${CUDA_VERSION_DASH} \
cuda-nvrtc-${CUDA_VERSION_DASH} \
cuda-cuobjdump-${CUDA_VERSION_DASH} \
libcurand-dev-${CUDA_VERSION_DASH} \
libcublas-${CUDA_VERSION_DASH} \
# Fixes nccl_allocator requiring nccl.h at runtime
# https://github.com/vllm-project/vllm/blob/1336a1ea244fa8bfd7e72751cabbdb5b68a0c11a/vllm/distributed/device_communicators/pynccl_allocator.py#L22
libnccl-dev && \
libcublas-${CUDA_VERSION_DASH} && \
# Fixes nccl_allocator requiring nccl.h at runtime
# https://github.com/vllm-project/vllm/blob/1336a1ea244fa8bfd7e72751cabbdb5b68a0c11a/vllm/distributed/device_communicators/pynccl_allocator.py#L22
# NCCL packages don't use the cuda-MAJOR-MINOR naming convention,
# so we pin the version to match our CUDA version
NCCL_VER=$(apt-cache madison libnccl-dev | grep "+cuda${CUDA_VERSION_SHORT}" | head -1 | awk -F'|' '{gsub(/^ +| +$/, "", $2); print $2}') && \
apt-get install -y --no-install-recommends --allow-change-held-packages libnccl-dev=${NCCL_VER} libnccl2=${NCCL_VER} && \
rm -rf /var/lib/apt/lists/*
# Install uv for faster pip installs
@@ -822,7 +826,7 @@ RUN --mount=type=cache,target=/root/.cache/uv \
uv pip install --system -r /tmp/kv_connectors.txt --no-build || ( \
# if the above fails, install from source
apt-get update -y && \
apt-get install -y --no-install-recommends ${BUILD_PKGS} && \
apt-get install -y --no-install-recommends --allow-change-held-packages ${BUILD_PKGS} && \
uv pip install --system -r /tmp/kv_connectors.txt --no-build-isolation && \
apt-get purge -y ${BUILD_PKGS} && \
# clean up -dev packages, keep runtime libraries