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: collect model ids to include in raise error message

Browse source
This commit is contained in:
Akram Ben Aissi 2025-10-08 22:51:59 +02:00
parent 24c6b01d16
commit 0ecfdc6dff
1 changed files with 6 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -82,11 +82,12 @@ class VLLMInferenceAdapter(OpenAIMixin):
Skip the check when running without authentication.
"""
if not self.config.api_token:
try:
return model in [m.id async for m in self.client.models.list()]
except Exception as e:
log.warning(f"Failed to check model availability: {e}")
raise ValueError(f"Failed to check model availability: {e}") from e
model_ids = []
async for m in self.client.models.list():
if m.id == model: # Found exact match
return True
model_ids.append(m.id)
raise ValueError(f"Model '{model}' not found. Available models: {model_ids}")
return True
async def openai_chat_completion(