set NCCL_IB_GID_INDEX=3 for multi node NVIDIA InfiniBand if needed (#3698)

benchmark/deepseek_v3/README.md

@@ -84,6 +84,8 @@ For example, there are two H20 nodes, each with 8 GPUs. The first node's IP is `
 
 If the command fails, try setting the `GLOO_SOCKET_IFNAME` parameter. For more information, see [Common Environment Variables](https://pytorch.org/docs/stable/distributed.html#common-environment-variables).
 
+If the multi nodes support NVIDIA InfiniBand and encounter hanging issues during startup, consider adding the parameter `export NCCL_IB_GID_INDEX=3`. For more information, see [this](https://github.com/sgl-project/sglang/issues/3516#issuecomment-2668493307).
+
 ```bash
 # node 1
 python3 -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V3 --tp 16 --dist-init-addr 10.0.0.1:5000 --nnodes 2 --node-rank 0 --trust-remote-code