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

Signed-off-by: Zhewen Li <zhewenli@inferact.ai>
Co-authored-by: Zhewen Li <zhewenli@inferact.ai>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
(cherry picked from commit 6232fb4b66b42c8e5f4ef1cc4c5163442cc99208)

docker/Dockerfile

@@ -540,7 +540,9 @@ RUN CUDA_VERSION_DASH=$(echo $CUDA_VERSION | cut -d. -f1,2 | tr '.' '-') && \
         libcurand-dev-${CUDA_VERSION_DASH} \
         libcublas-${CUDA_VERSION_DASH} \
         # 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
     # 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,