phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 19:00:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix again vllm

Browse source
This commit is contained in:
Xi Yan 2025-01-17 17:50:25 -08:00
parent 3e7496e835
commit 9a0fa89e9a
2 changed files with 3 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -177,7 +177,8 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
if isinstance(request, ChatCompletionRequest):
if media_present:
input_dict["messages"] = [
await convert_message_to_openai_dict(m) for m in request.messages
await convert_message_to_openai_dict(m, download=True)
for m in request.messages
]
else:
input_dict["prompt"] = await chat_completion_request_to_prompt(