docker run -d --name dsv4pro_pro6000d_2node_sglang_tp16_quick_map_worker --gpus all --network host --ipc host --shm-size 20g --ulimit memlock=-1 --ulimit stack=67108864 -v /data/hf_models/DeepSeek-V4-Pro:/data/hf_models/DeepSeek-V4-Pro:ro -v /data/hzy/sglang_cache/dsv4_pro_tp16:/root/.cache -e CUDA_VISIBLE_DEVICES=0\,1\,2\,3\,4\,5\,6\,7 -e PYTHONUNBUFFERED=1 -e HF_HUB_OFFLINE=1 -e TRANSFORMERS_OFFLINE=1 -e PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True -e NCCL_SOCKET_IFNAME=eth0 -e NCCL_IB_HCA==mlx5_0:1\,mlx5_3:1 -e NCCL_CROSS_NIC=1 -e NCCL_DEBUG=INFO -e SGLANG_SHARED_EXPERT_TP1=1 --device /dev/infiniband/rdma_cm --device /dev/infiniband/uverbs0 --device /dev/infiniband/uverbs3 --entrypoint python3 lmsysorg/sglang:nightly-dev-cu13-20260720-b3570a45 -m sglang.launch_server --model-path /data/hf_models/DeepSeek-V4-Pro --tp-size 16 --ep-size 2 --nnodes 2 --node-rank 1 --dist-init-addr 10.101.0.11:20002 --trust-remote-code --host 0.0.0.0 --port 30002 --mem-fraction-static 0.9 --cuda-graph-max-bs-decode 64 --max-running-requests 256 
