Qwen
/

Text Generation
Transformers
Safetensors
qwen3_moe
conversational
JustinLin610 zhyncs commited on
Commit
b51c430
·
verified ·
1 Parent(s): 0412748

fix: use tp 8 for SGLang (#1)

Browse files

- fix: use tp 4 for SGLang (61b44baf50859854ff2f1838bd25b2478583e0a6)
- Update README.md (65f3e39e1083de010a45e40c49af1707505d9371)


Co-authored-by: Yineng Zhang <[email protected]>

Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -95,7 +95,7 @@ print("content:", content)
95
  For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.5` or to create an OpenAI-compatible API endpoint:
96
  - SGLang:
97
  ```shell
98
- python -m sglang.launch_server --model-path Qwen/Qwen3-235B-A22B --reasoning-parser qwen3
99
  ```
100
  - vLLM:
101
  ```shell
 
95
  For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.5` or to create an OpenAI-compatible API endpoint:
96
  - SGLang:
97
  ```shell
98
+ python -m sglang.launch_server --model-path Qwen/Qwen3-235B-A22B --reasoning-parser qwen3 --tp 8
99
  ```
100
  - vLLM:
101
  ```shell