EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Lianmin Zheng
2024-07-09 01:52:55 -07:00
parent ce62dc73f0
commit da2e5d6546
2 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

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

2
python/sglang/srt/openai_protocol.py
View File

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