Include context length in /v1/models response. (#4809)

This commit is contained in:
Jon Durbin
2025-03-27 23:23:18 -04:00
committed by GitHub
parent e84f4ba0ab
commit 04eb6062e4
3 changed files with 14 additions and 1 deletions

View File

@@ -28,6 +28,7 @@ class ModelCard(BaseModel):
created: int = Field(default_factory=lambda: int(time.time()))
owned_by: str = "sglang"
root: Optional[str] = None
max_model_len: Optional[int] = None
class ModelList(BaseModel):