Fix max_tokens for OpenAI chat completion API (#766)

2024-07-27 15:44:27 -07:00
parent de854fb5c5
commit f95e661757
3 changed files with 24 additions and 21 deletions
--- a/python/sglang/srt/openai_api/protocol.py
+++ b/python/sglang/srt/openai_api/protocol.py
@@ -152,7 +152,7 @@ class ChatCompletionRequest(BaseModel):
    logit_bias: Optional[Dict[str, float]] = None
    logprobs: Optional[bool] = False
    top_logprobs: Optional[int] = None
-    max_tokens: Optional[int] = 16
+    max_tokens: Optional[int] = None
    n: Optional[int] = 1
    presence_penalty: Optional[float] = 0.0
    response_format: Optional[ResponseFormat] = None