[CI/Build] Fixes missing runtime dependencies (#29822)

Signed-off-by: bbartels <benjamin@bartels.dev>
(cherry picked from commit 2d613de9)

docker/Dockerfile

@@ -364,7 +364,12 @@ RUN CUDA_VERSION_DASH=$(echo $CUDA_VERSION | cut -d. -f1,2 | tr '.' '-') && \
     cuda-cudart-${CUDA_VERSION_DASH} \
     cuda-nvrtc-${CUDA_VERSION_DASH} \
     cuda-cuobjdump-${CUDA_VERSION_DASH} \
-    libcublas-${CUDA_VERSION_DASH} && \
+    # https://github.com/vllm-project/vllm/issues/29590
+    libcurand-dev-${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 && \
     rm -rf /var/lib/apt/lists/*
 
 ARG PIP_INDEX_URL UV_INDEX_URL