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

Improve process creation (#1534)

Browse Source
This commit is contained in:
Lianmin Zheng
2024-09-29 02:36:12 -07:00
committed by GitHub
parent fd9ad817ec
commit 048685430d
15 changed files with 270 additions and 677 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/en/backend.md
View File

@@ -84,7 +84,7 @@ python -m sglang.launch_server --model-path meta-llama/Meta-Llama-3-8B-Instruct
- To enable fp8 weight quantization, add `--quantization fp8` on a fp16 checkpoint or directly load a fp8 checkpoint without specifying any arguments.
- To enable fp8 kv cache quantization, add `--kv-cache-dtype fp8_e5m2`.
- If the model does not have a chat template in the Hugging Face tokenizer, you can specify a [custom chat template](https://sglang.readthedocs.io/en/latest/custom_chat_template.html).
- 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.
- 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