docker run -d --name kimi3_pro6000_dp2_nospec_ab_tp32_b_2 --gpus all --network host --ipc=host --shm-size 32g --ulimit memlock=-1 --device /dev/infiniband -v /data/hf_models/Kimi-K3:/data/hf_models/Kimi-K3:ro -v /data/hzy/cache/kimi-dflash-fi0618-situ4460:/cache -e SGLANG_HOST_IP=174.1.60.7 -e PYTHONUNBUFFERED=1 -e HF_HUB_OFFLINE=1 -e TRANSFORMERS_OFFLINE=1 -e GLOO_SOCKET_IFNAME=bond0 -e NCCL_SOCKET_IFNAME=bond1 -e NCCL_IB_HCA=mlx5_0\,mlx5_1\,mlx5_2\,mlx5_3 -e NCCL_IB_GID_INDEX=3 -e NCCL_IB_TIMEOUT=22 -e NCCL_IB_RETRY_CNT=7 -e NCCL_CUMEM_ENABLE=1 -e NCCL_DEBUG=WARN -e NCCL_DEBUG_SUBSYS=INIT\,ENV -e PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True -e SGLANG_ENABLE_TP_MEMORY_INBALANCE_CHECK=0 -e SGLANG_MOE_FUSED_GATE_RADIX=1 -e FLASHINFER_WORKSPACE_BASE=/cache -e FLASHINFER_CUDA_ARCH_LIST=12.0f -e SGLANG_CACHE_DIR=/cache -e XDG_CACHE_HOME=/cache -e TRITON_CACHE_DIR=/cache/triton -e TORCH_EXTENSIONS_DIR=/cache/torch_extensions -e CUDA_CACHE_PATH=/cache/cuda -e TMPDIR=/cache/tmp -e MAX_JOBS=4 --entrypoint python3 local/sglang:kimi-k3-pp-dflash-33863-fi0618-situ4460-kvbounds1 -m sglang.launch_server --model-path /data/hf_models/Kimi-K3 --served-model-name kimi-k3 --trust-remote-code --tp-size 32 --pp-size 1 --ep-size 4 --nnodes 4 --node-rank 2 --dist-init-addr 174.1.60.5:20000 --moe-runner-backend flashinfer_mxfp4 --moe-a2a-backend none --kv-cache-dtype bfloat16 --chunked-prefill-size 8192 --page-size 64 --mem-fraction-static 0.86 --mamba-full-memory-ratio 0.21 --mamba-radix-cache-strategy extra_buffer_lazy --disable-radix-cache --max-running-requests 8 --cuda-graph-max-bs-decode 8 --dist-timeout 3600 --enable-metrics --enable-request-time-stats-logging --host 0.0.0.0 --port 30000
