phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-12 12:06:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

review: add warning when not checking mode availability for vllm

Browse source
This commit is contained in:
Akram Ben Aissi 2025-10-08 23:11:25 +02:00
parent 0ecfdc6dff
commit fbd4ae8dae
1 changed files with 1 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -88,6 +88,7 @@ class VLLMInferenceAdapter(OpenAIMixin):
return True
model_ids.append(m.id)
raise ValueError(f"Model '{model}' not found. Available models: {model_ids}")
log.warning(f"Not checking model availability for {model} as API token may trigger OAuth workflow")
return True
async def openai_chat_completion(