squall/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Frontend][OpenAI] Support for returning max_model_len on /v1/models response (#4643)

Browse Source
This commit is contained in:
Avinash Raj 2024-06-02 13:36:13 +05:30 committed by GitHub
parent ed59a7ed23
commit f790ad3c50
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
vllm/entrypoints/openai/protocol.py
View File

@ -82,6 +82,7 @@ class ModelCard(OpenAIBaseModel):
owned_by: str = "vllm" owned_by: str = "vllm"
root: Optional[str] = None root: Optional[str] = None
parent: Optional[str] = None parent: Optional[str] = None
max_model_len: Optional[int] = None
permission: List[ModelPermission] = Field(default_factory=list) permission: List[ModelPermission] = Field(default_factory=list)

1
vllm/entrypoints/openai/serving_engine.py
View File

@ -62,6 +62,7 @@ class OpenAIServing:
"""Show available models. Right now we only have one model.""" """Show available models. Right now we only have one model."""
model_cards = [ model_cards = [
ModelCard(id=served_model_name, ModelCard(id=served_model_name,
max_model_len=self.max_model_len,
root=self.served_model_names[0], root=self.served_model_names[0],
permission=[ModelPermission()]) permission=[ModelPermission()])
for served_model_name in self.served_model_names for served_model_name in self.served_model_names