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

Improve tensor parallel performance (#625)

Browse Source 
Co-authored-by: Mingyi <wisclmy0611@gmail.com>
This commit is contained in:
Ying Sheng
2024-07-15 07:10:51 -07:00
committed by GitHub
parent 5ac8b80677
commit 6a2941f4d0
10 changed files with 171 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@@ -377,6 +377,14 @@ python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port
python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --port 30000 --mem-fraction-static 0.7
```
- See [hyperparameter_tuning.md](docs/hyperparameter_tuning.md) on tuning hyperparameters for better performance.
- Add `--nnodes 2` to run tensor parallelism on multiple nodes. If you have two nodes with two GPUs on each node and want to run TP=4, let `sgl-dev-1` be the hostname of the first node and `50000` be an available port.
```
# Node 0
python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --tp 4 --nccl-init sgl-dev-1:50000 --nnodes 2 --node-rank 0
# Node 1
python -m sglang.launch_server --model-path meta-llama/Llama-2-7b-chat-hf --tp 4 --nccl-init sgl-dev-1:50000 --nnodes 2 --node-rank 1
```
### Supported Models
- Llama