phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 01:03:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Apply formatting to source files

Browse source
This commit is contained in:
Fred Reiss 2024-12-19 11:46:31 -08:00
parent 6ec9eabbeb
commit c8580d3b0c
2 changed files with 15 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

11
llama_stack/providers/inline/inference/vllm/vllm.py
View file

@ -102,9 +102,11 @@ class VLLMInferenceImpl(Inference, ModelsProtocolPrivate):
registered_model = resolve_model(model.model_id)
if configured_model.core_model_id != registered_model.core_model_id:
raise ValueError(f"Requested model '{model.identifier}' is different from "
raise ValueError(
f"Requested model '{model.identifier}' is different from "
f"model '{self.config.model}' that this provider "
f"is configured to serve")
f"is configured to serve"
)
return model
def _sampling_params(self, sampling_params: SamplingParams) -> VLLMSamplingParams:
@ -169,8 +171,9 @@ class VLLMInferenceImpl(Inference, ModelsProtocolPrivate):
log.info("Sampling params: %s", sampling_params)
request_id = _random_uuid()
prompt = await chat_completion_request_to_prompt(request, self.config.model,
self.formatter)
prompt = await chat_completion_request_to_prompt(
request, self.config.model, self.formatter
)
vllm_sampling_params = self._sampling_params(request.sampling_params)
results_generator = self.engine.generate(
prompt, vllm_sampling_params, request_id