phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-12 13:00:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: Unregister a model from registry if not being served

Browse source 
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
This commit is contained in:
Yuan Tang 2025-02-20 13:04:15 -05:00
parent b890d7a611
commit 6abfe0c43b
No known key found for this signature in database
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -231,7 +231,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
pass
async def unregister_model(self, model_id: str) -> None:
pass
await self.register_helper.unregister_model(model_id)
async def completion(
self,
@ -342,6 +342,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
res = self.client.models.list()
available_models = [m.id for m in res]
if model.provider_resource_id not in available_models:
await self.unregister_model(model.provider_resource_id)
raise ValueError(
f"Model {model.provider_resource_id} is not being served by vLLM. "
f"Available models: {', '.join(available_models)}"