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

migrate inference/completion

Browse source
This commit is contained in:
Xi Yan 2024-09-11 12:29:22 -07:00
parent 0c7c6b7e02
commit a7be58e4e1
2 changed files with 6 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

1
llama_toolchain/inference/meta_reference/inference.py
View file

@ -65,6 +65,7 @@ class MetaReferenceInferenceImpl(Inference):
) -> AsyncIterator[
Union[ChatCompletionResponseStreamChunk, ChatCompletionResponse]
]:
# wrapper request to make it easier to pass around (internal only, not exposed to API)
request = ChatCompletionRequest(
model=model,
messages=messages,