fix: use tp 8 for SGLang

README.md

@@ -95,7 +95,7 @@ print("content:", content)
 For deployment, you can use `sglang>=0.4.6.post1` or `vllm>=0.8.4` or  to create an OpenAI-compatible API endpoint:
 - SGLang:
     ```shell
-    python -m sglang.launch_server --model-path Qwen/Qwen3-235B-A22B --reasoning-parser qwen3
+    python -m sglang.launch_server --model-path Qwen/Qwen3-235B-A22B --reasoning-parser qwen3 --tp 8
     ```
 - vLLM:
     ```shell