拉取的docker如下:
export IMAGE=image.sourcefind.cn:5000/dcu/admin/base/custom:vllm0.9.2-ubuntu22.04-dtk25.04-das1.6-py3.10-20250916-rc2
docker run -itd
--shm-size 200g
--network=host
--name development
--privileged
--device=/dev/kfd
--device=/dev/dri
--device=/dev/mkfd
--group-add video
--cap-add=SYS_PTRACE
--security-opt seccomp=unconfined
-u root
-v /opt/hyhal/:/opt/hyhal/:ro
-v /htxjj:/data
-e ALLREDUCE_STREAM_WITH_COMPUTE=1
-e HSA_FORCE_FINE_GRAIN_PCIE=1
-e NCCL_IB_HCA=mlx5_0:1
-e NCCL_IB_DISABLE=0
-e NCCL_MAX_NCHANNELS=16
-e NCCL_MIN_NCHANNELS=16
-e NCCL_NET_GDR_READ=1
-e NCCL_DEBUG=INFO
-e NCCL_MIN_P2P_NCHANNELS=16
-e NCCL_NCHANNELS_PER_PEER=16
-e HIP_USE_GRAPH_QUEUE_POOL=1
-e VLLM_ENABLE_MOE_FUSED_GATE=0
-e VLLM_ENFORCE_EAGER_BS_THRESHOLD=44
-e VLLM_RPC_TIMEOUT=1800000
$IMAGE bash
#-e NCCL_SOCKET_IFNAME
#-e GLOO_SOCKET_IFNAME