phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-01 19:40:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix vllm base64

Browse source
This commit is contained in:
Xi Yan 2025-01-17 16:17:15 -08:00
parent 9d005154d7
commit 6d21da6e48
2 changed files with 43 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -176,10 +176,8 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
media_present = request_has_media(request)
if isinstance(request, ChatCompletionRequest):
if media_present:
# vllm does not seem to work well with image urls, so we download the images
input_dict["messages"] = [
await convert_message_to_openai_dict(m, download=True)
for m in request.messages
await convert_message_to_openai_dict(m) for m in request.messages
]
else:
input_dict["prompt"] = await chat_completion_request_to_prompt(