phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 06:52:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(vllm): periodically refresh models

Browse source
This commit is contained in:
Ashwin Bharambe 2025-07-18 15:33:33 -07:00
parent 68a2dfbad7
commit 1bf710bec0
6 changed files with 95 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/apis/inference/inference.py
View file

@ -819,7 +819,7 @@ class OpenAIEmbeddingsResponse(BaseModel):
class ModelStore(Protocol):
async def get_model(self, identifier: str) -> Model: ...
async def update_registered_models(
async def update_registered_llm_models(
self,
provider_id: str,
models: list[Model],