phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: remove /v1/inference/completion and implementations

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-30 03:46:07 -04:00
parent 606f4cf281
commit 4b641d7127
78 changed files with 16143 additions and 17755 deletions
Download patch file Download diff file Expand all files Collapse all files

41
llama_stack/core/routers/inference.py
View file

@ -267,47 +267,6 @@ class InferenceRouter(Inference):
)
return response
async def completion(
self,
model_id: str,
content: InterleavedContent,
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
stream: bool | None = False,
logprobs: LogProbConfig | None = None,
) -> AsyncGenerator:
if sampling_params is None:
sampling_params = SamplingParams()
logger.debug(
f"InferenceRouter.completion: {model_id=}, {stream=}, {content=}, {sampling_params=}, {response_format=}",
)
model = await self._get_model(model_id, ModelType.llm)
provider = await self.routing_table.get_provider_impl(model_id)
params = dict(
model_id=model_id,
content=content,
sampling_params=sampling_params,
response_format=response_format,
stream=stream,
logprobs=logprobs,
)
prompt_tokens = await self._count_tokens(content)
response = await provider.completion(**params)
if stream:
return self.stream_tokens_and_compute_metrics(
response=response,
prompt_tokens=prompt_tokens,
model=model,
)
metrics = await self.count_tokens_and_compute_metrics(
response=response, prompt_tokens=prompt_tokens, model=model
)
response.metrics = metrics if response.metrics is None else response.metrics + metrics
return response
async def openai_completion(
self,
model: str,