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/references/llama_405B.md
View File

@@ -11,9 +11,9 @@ python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-405B-Instr
```bash
# on the first node, replace 172.16.4.52:20000 with your own node ip address and port
python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-405B-Instruct --tp 16 --nccl-init-addr 172.16.4.52:20000 --nnodes 2 --node-rank 0
python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-405B-Instruct --tp 16 --dist-init-addr-addr 172.16.4.52:20000 --nnodes 2 --node-rank 0
# on the second node, replace 172.18.45.52:20000 with your own node ip address and port
python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-405B-Instruct --tp 16 --nccl-init-addr 172.18.45.52:20000 --nnodes 2 --node-rank 1
python3 -m sglang.launch_server --model-path meta-llama/Meta-Llama-3.1-405B-Instruct --tp 16 --dist-init-addr-addr 172.18.45.52:20000 --nnodes 2 --node-rank 1
```