Skip to content

GitLab

"...git@developer.sourcefind.cn:2222/OpenDAS/vllm_cscc.git" did not exist on "77073c77bc2006eb80ea6d5128f076f5e6c6f54f"
Commit 88d34c64 authored by Zhewen Li's avatar Zhewen Li Committed by khluu
Browse files

[Docker] Install numactl CLI in CUDA runtime image (#41032) 


Signed-off-by: default avatarZhewen Li <zhewenli@inferact.ai>
Co-authored-by: default avatarZhewen Li <zhewenli@inferact.ai>
Co-authored-by: default avatarClaude Opus 4.7 (1M context) <noreply@anthropic.com>
(cherry picked from commit 6232fb4b66b42c8e5f4ef1cc4c5163442cc99208)
parent b8160878
Hide whitespace changes
Inline Side-by-side
Showing with 3 additions and 1 deletion
docker/Dockerfile
View file @ 88d34c64
...@@ -540,7 +540,9 @@ RUN CUDA_VERSION_DASH=$(echo $CUDA_VERSION | cut -d. -f1,2 | tr '.' '-') && \ ...@@ -540,7 +540,9 @@ RUN CUDA_VERSION_DASH=$(echo $CUDA_VERSION | cut -d. -f1,2 | tr '.' '-') && \
libcurand-dev-${CUDA_VERSION_DASH} \ libcurand-dev-${CUDA_VERSION_DASH} \
libcublas-${CUDA_VERSION_DASH} \ libcublas-${CUDA_VERSION_DASH} \
# Required by fastsafetensors (fixes #20384) # Required by fastsafetensors (fixes #20384)
libnuma-dev && \ libnuma-dev \
# numactl CLI for NUMA binding at runtime
numactl && \
# Fixes nccl_allocator requiring nccl.h at runtime # Fixes nccl_allocator requiring nccl.h at runtime
# https://github.com/vllm-project/vllm/blob/1336a1ea244fa8bfd7e72751cabbdb5b68a0c11a/vllm/distributed/device_communicators/pynccl_allocator.py#L22 # 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, # NCCL packages don't use the cuda-MAJOR-MINOR naming convention,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment