phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-01 20:18:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add suffix to openai.completions

Browse source
This commit is contained in:
Hardik Shah 2025-06-13 15:39:45 -07:00
parent e2e15ebb6c
commit 1cfb5b1205
15 changed files with 101 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama_stack/providers/remote/inference/nvidia/nvidia.py
View file

@ -316,6 +316,7 @@ class NVIDIAInferenceAdapter(Inference, ModelRegistryHelper):
user: str | None = None,
guided_choice: list[str] | None = None,
prompt_logprobs: int | None = None,
suffix: str | None = None,
) -> OpenAICompletion:
provider_model_id = await self._get_provider_model_id(model)