phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-16 14:57:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

address feedback

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-11-08 16:11:53 -08:00
parent 772e23e29e
commit d6a9a17828
4 changed files with 2 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/inline/inference/vllm/vllm.py
View file

@ -88,14 +88,6 @@ class VLLMInferenceImpl(Inference, ModelsProtocolPrivate):
"You cannot dynamically add a model to a running vllm instance"
)
async def list_models(self) -> List[Model]:
return [
Model(
identifier=self.config.model,
llama_model=self.config.model,
)
]
def _sampling_params(self, sampling_params: SamplingParams) -> VLLMSamplingParams:
if sampling_params is None:
return VLLMSamplingParams(max_tokens=self.config.max_tokens)