Fix the default argument of OpenAI Chat completion (#605)

README.md

@@ -42,7 +42,6 @@ pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.3/
 git clone https://github.com/sgl-project/sglang.git
 cd sglang
 
-pip install --upgrade pip
 pip install -e "python[all]"
 
 # Install FlashInfer CUDA kernels

python/sglang/srt/openai_protocol.py

@@ -134,7 +134,7 @@ class ChatCompletionRequest(BaseModel):
     logit_bias: Optional[Dict[str, float]] = None
     logprobs: Optional[bool] = False
     top_logprobs: Optional[int] = None
-    max_tokens: Optional[int] = None
+    max_tokens: Optional[int] = 16
     n: Optional[int] = 1
     presence_penalty: Optional[float] = 0.0
     response_format: Optional[ResponseFormat] = None