Skip to content

Commit 9dc83e2

Browse files
committed
add disable think note
1 parent 58afa36 commit 9dc83e2

File tree

1 file changed

+3
-0
lines changed

1 file changed

+3
-0
lines changed

docs/user_guide/quick_start.md

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -130,6 +130,9 @@ curl --location 'http://localhost:3001/v1/chat/completions' --header 'Content-Ty
130130
}'
131131
```
132132

133+
> **Note:**
134+
For models such as Qwen3 and gpt-oss, the "reasoning" (or "thinking") feature is enabled by default. To disable it, add `"chat_template_kwargs": {"enable_thinking": false}` to your request payload.
135+
133136
### Skipping Scheduler
134137
Developers can start Parallax backend engine without a scheduler. Pipeline parallel start/end layers should be set manually.
135138
An example of serving Qwen3-0.6B with 2-nodes:

0 commit comments

Comments
 (0)