phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 06:29:40 +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

6
llama_stack/distribution/routing_tables/models.py
View file

@ -81,7 +81,7 @@ class ModelsRoutingTable(CommonRoutingTableImpl, Models):
raise ValueError(f"Model {model_id} not found")
await self.unregister_object(existing_model)
async def update_registered_models(
async def update_registered_llm_models(
self,
provider_id: str,
models: list[Model],
@ -92,12 +92,14 @@ class ModelsRoutingTable(CommonRoutingTableImpl, Models):
# from run.yaml) that we need to keep track of
model_ids = {}
for model in existing_models:
if model.provider_id == provider_id:
if model.provider_id == provider_id and model.model_type == ModelType.llm:
model_ids[model.provider_resource_id] = model.identifier
logger.debug(f"unregistering model {model.identifier}")
await self.unregister_object(model)
for model in models:
if model.model_type != ModelType.llm:
continue
if model.provider_resource_id in model_ids:
model.identifier = model_ids[model.provider_resource_id]