EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Support multi-node DP attention (#2925)

Browse Source 
Co-authored-by: dhou-xai <dhou@x.ai>
This commit is contained in:
Lianmin Zheng
2025-01-16 11:15:00 -08:00
committed by GitHub
parent 58f3f2b840
commit 8b6ce52e92
16 changed files with 287 additions and 137 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/backend/server_arguments.md
View File

@@ -26,8 +26,8 @@ python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct
- To run tensor parallelism on multiple nodes, add `--nnodes 2`. If you have two nodes with two GPUs on each node and want to run TP=4, let `sgl-dev-0` be the hostname of the first node and `50000` be an available port, you can use the following commands. If you meet deadlock, please try to add `--disable-cuda-graph`
```
# Node 0
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --tp 4 --nccl-init sgl-dev-0:50000 --nnodes 2 --node-rank 0
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --tp 4 --dist-init-addr sgl-dev-0:50000 --nnodes 2 --node-rank 0
# Node 1
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --tp 4 --nccl-init sgl-dev-0:50000 --nnodes 2 --node-rank 1
python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct --tp 4 --dist-init-addr sgl-dev-0:50000 --nnodes 2 --node-rank 1
```