phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 03:50:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix register_model protocol to return Model

Browse source 
Signed-off-by: Ihar Hrachyshka <ihar.hrachyshka@gmail.com>
This commit is contained in:
Ihar Hrachyshka 2025-03-26 17:34:53 +00:00
parent 58a040a805
commit 6df600f014
5 changed files with 8 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -346,7 +346,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
async for chunk in process_completion_stream_response(stream):
yield chunk
async def register_model(self, model: Model) -> None:
async def register_model(self, model: Model) -> Model:
assert self.client is not None
model = await self.register_helper.register_model(model)
res = await self.client.models.list()
@ -356,6 +356,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
f"Model {model.provider_resource_id} is not being served by vLLM. "
f"Available models: {', '.join(available_models)}"
)
return model
async def _get_params(self, request: Union[ChatCompletionRequest, CompletionRequest]) -> dict:
options = get_sampling_options(request.sampling_params)