phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 09:21:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Bug fixes for together.ai OpenAI endpoints

Browse source 
After actually running the test_openai_completion.py tests against
together.ai, turns out there were a couple of bugs in the initial
implementation. This fixes those.

Signed-off-by: Ben Browning <bbrownin@redhat.com>
This commit is contained in:
Ben Browning 2025-04-10 14:19:48 -04:00
parent a5827f7cb3
commit ffae192540
1 changed files with 2 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/remote/inference/together/together.py
View file

@ -279,7 +279,7 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi
guided_choice: Optional[List[str]] = None,
prompt_logprobs: Optional[int] = None,
) -> OpenAICompletion:
model_obj = await self._get_model(model)
model_obj = await self.model_store.get_model(model)
params = await prepare_openai_completion_params(
model=model_obj.provider_resource_id,
prompt=prompt,
@ -298,8 +298,6 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi
temperature=temperature,
top_p=top_p,
user=user,
guided_choice=guided_choice,
prompt_logprobs=prompt_logprobs,
)
return await self._get_openai_client().completions.create(**params) # type: ignore
@ -329,7 +327,7 @@ class TogetherInferenceAdapter(ModelRegistryHelper, Inference, NeedsRequestProvi
top_p: Optional[float] = None,
user: Optional[str] = None,
) -> OpenAIChatCompletion:
model_obj = await self._get_model(model)
model_obj = await self.model_store.get_model(model)
params = await prepare_openai_completion_params(
model=model_obj.provider_resource_id,
messages=messages,