sglang icon indicating copy to clipboard operation
sglang copied to clipboard
Published 1 month ago • verified publisher icon sgl-project

[Bug] TCPStore Error processing client message: Too many keys being waited. keys: 3891110078061282660, max: 13107

Open Superskyyy opened this issue 10 months ago • 2 comments

Checklist

  • [x] 1. I have searched related issues but cannot get the expected help.
  • [x] 2. The bug has not been fixed in the latest version.
  • [x] 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.
  • [ ] 4. If the issue you raised is not a bug but a question, please raise a discussion at https://github.com/sgl-project/sglang/discussions/new/choose Otherwise, it will be closed.
  • [x] 5. Please use English, otherwise it will be closed.

Describe the bug

Image

Reproduction

Start on Two nodes of H100, with NCCL IB and below command:

docker run --gpus all \
    --shm-size 64g \
    --network=host \
    --privileged \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    -v /home/xxx:/home/xxx\
    --name sglang_multinode1 \
    -it \
    -e NCCL_SOCKET_IFNAME=ib0 \
    -e NCCL_DEBUG=INFO \
    -e GLOO_SOCKET_IFNAME=ib0 \
    -e GLOO_DEBUG=INFO \
    --rm \
    --env "HF_TOKEN=$HF_TOKEN" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server --model-path /home/xxx/deepseek-r1 --tp 16 --dist-init-addr IP:20000 --nnodes 2 --node-rank 0 --trust-remote-code --host localhost --port 1105 --enable-torch-compile --torch-compile-max-bs 8 --api-key=xxxxx

docker run --gpus all \
    --shm-size 64g \
    --network=host \
    --privileged \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    -v /home/xxx:/home/xxx\
    --name sglang_multinode2 \
    -it \
    -e NCCL_SOCKET_IFNAME=ib0 \
    -e NCCL_DEBUG=INFO \
    -e GLOO_SOCKET_IFNAME=ib0 \
    -e GLOO_DEBUG=INFO \
    --rm \
    --env "HF_TOKEN=$HF_TOKEN" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server --model-path /home/xxx/deepseek-r1 --tp 16 --dist-init-addr IP:20000 --nnodes 2 --node-rank 1 --trust-remote-code --host localhost --port 1105 --enable-torch-compile --torch-compile-max-bs 8 --api-key=xxxxx

Environment

INFO 02-20 03:28:59 init.py:190] Automatically detected platform cuda. Python: 3.12.8 (main, Jan 27 2025, 17:53:37) [GCC 11.4.0] CUDA available: True GPU 0,1,2,3,4,5,6,7: NVIDIA H100 80GB HBM3 GPU 0,1,2,3,4,5,6,7 Compute Capability: 9.0 CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 12.4, V12.4.131 CUDA Driver Version: 550.127.05 PyTorch: 2.5.1+cu124 sgl_kernel: 0.0.3.post6 flashinfer: 0.2.1.post2+cu124torch2.5 triton: 3.1.0 transformers: 4.48.3 torchao: 0.8.0 numpy: 1.26.4 aiohttp: 3.11.12 fastapi: 0.115.8 hf_transfer: 0.1.9 huggingface_hub: 0.29.0 interegular: 0.3.3 modelscope: 1.23.0 orjson: 3.10.15 packaging: 24.2 psutil: 7.0.0 pydantic: 2.10.6 multipart: 0.0.20 zmq: 26.2.1 uvicorn: 0.34.0 uvloop: 0.21.0 vllm: 0.7.2 openai: 1.63.2 tiktoken: 0.9.0 anthropic: 0.46.0 decord: 0.6.0 NVIDIA Topology: GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 NIC8 CPU Affinity NUMA Affinity GPU NUMA ID GPU0 X NV18 NV18 NV18 NV18 NV18 NV18 NV18 PIX NODE NODE NODE SYS SYS SYS SYS NODE 0-55,112-167 0 N/A GPU1 NV18 X NV18 NV18 NV18 NV18 NV18 NV18 NODE PIX NODE NODE SYS SYS SYS SYS NODE 0-55,112-167 0 N/A GPU2 NV18 NV18 X NV18 NV18 NV18 NV18 NV18 NODE NODE PIX NODE SYS SYS SYS SYS NODE 0-55,112-167 0 N/A GPU3 NV18 NV18 NV18 X NV18 NV18 NV18 NV18 NODE NODE NODE PIX SYS SYS SYS SYS NODE 0-55,112-167 0 N/A GPU4 NV18 NV18 NV18 NV18 X NV18 NV18 NV18 SYS SYS SYS SYS PIX NODE NODE NODE SYS 56-111,168-223 1 N/A GPU5 NV18 NV18 NV18 NV18 NV18 X NV18 NV18 SYS SYS SYS SYS NODE PIX NODE NODE SYS 56-111,168-223 1 N/A GPU6 NV18 NV18 NV18 NV18 NV18 NV18 X NV18 SYS SYS SYS SYS NODE NODE PIX NODE SYS 56-111,168-223 1 N/A GPU7 NV18 NV18 NV18 NV18 NV18 NV18 NV18 X SYS SYS SYS SYS NODE NODE NODE PIX SYS 56-111,168-223 1 N/A NIC0 PIX NODE NODE NODE SYS SYS SYS SYS X NODE NODE NODE SYS SYS SYS SYS NODE NIC1 NODE PIX NODE NODE SYS SYS SYS SYS NODE X NODE NODE SYS SYS SYS SYS NODE NIC2 NODE NODE PIX NODE SYS SYS SYS SYS NODE NODE X NODE SYS SYS SYS SYS NODE NIC3 NODE NODE NODE PIX SYS SYS SYS SYS NODE NODE NODE X SYS SYS SYS SYS NODE NIC4 SYS SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS X NODE NODE NODE SYS NIC5 SYS SYS SYS SYS NODE PIX NODE NODE SYS SYS SYS SYS NODE X NODE NODE SYS NIC6 SYS SYS SYS SYS NODE NODE PIX NODE SYS SYS SYS SYS NODE NODE X NODE SYS NIC7 SYS SYS SYS SYS NODE NODE NODE PIX SYS SYS SYS SYS NODE NODE NODE X SYS NIC8 NODE NODE NODE NODE SYS SYS SYS SYS NODE NODE NODE NODE SYS SYS SYS SYS X

Legend:

X = Self SYS = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI) NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node PHB = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU) PXB = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge) PIX = Connection traversing at most a single PCIe bridge NV# = Connection traversing a bonded set of # NVLinks

NIC Legend:

NIC0: mlx5_0 NIC1: mlx5_1 NIC2: mlx5_2 NIC3: mlx5_5 NIC4: mlx5_6 NIC5: mlx5_7 NIC6: mlx5_8 NIC7: mlx5_9 NIC8: mlx5_bond_0

ulimit soft: 1048576

Superskyyy avatar Feb 20 '25 03:02 Superskyyy

@FrankLeeeee Could you please have a look

Fridge003 avatar Feb 20 '25 04:02 Fridge003

@FrankLeeeee Could you please have a look

Ok, let me take a look

FrankLeeeee avatar Feb 20 '25 04:02 FrankLeeeee

This issue has been automatically closed due to inactivity. Please feel free to reopen it if needed.

github-actions[bot] avatar Apr 22 '25 00:04 github-actions[bot]