phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-02 08:44:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

live listing overrides static listing for ollama & vllm model registration

Browse source
This commit is contained in:
Matthew Farrellee 2025-04-27 10:44:45 -04:00
parent a4c8a849b6
commit c590674ee2
2 changed files with 8 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

5
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -333,7 +333,10 @@ class OllamaInferenceAdapter(
return EmbeddingsResponse(embeddings=embeddings)
async def register_model(self, model: Model) -> Model:
model = await self.register_helper.register_model(model)
try:
model = await self.register_helper.register_model(model)
except ValueError:
pass # Ignore statically unknown model, will check live listing
if model.model_type == ModelType.embedding:
logger.info(f"Pulling embedding model `{model.provider_resource_id}` if necessary...")
await self.client.pull(model.provider_resource_id)

5
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -358,7 +358,10 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
async def register_model(self, model: Model) -> Model:
assert self.client is not None
model = await self.register_helper.register_model(model)
try:
model = await self.register_helper.register_model(model)
except ValueError:
pass # Ignore statically unknown model, will check live listing
res = await self.client.models.list()
available_models = [m.id async for m in res]
if model.provider_resource_id not in available_models: