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

fix(dev): fix vllm inference recording (await models.list)

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-23 10:33:55 -04:00
parent a7f9ce9a3a
commit 3ea30c0a9c
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -504,7 +504,7 @@ class VLLMInferenceAdapter(OpenAIMixin, LiteLLMOpenAIMixin, Inference, ModelsPro
except ValueError:
pass # Ignore statically unknown model, will check live listing
try:
res = await self.client.models.list()
res = self.client.models.list()
except APIConnectionError as e:
raise ValueError(
f"Failed to connect to vLLM at {self.config.url}. Please check if vLLM is running and accessible at that URL."