phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-29 15:23:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix inference

Browse source
This commit is contained in:
Xi Yan 2024-09-11 14:51:06 -07:00
parent 96f3058145
commit 2d0163b47b
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_toolchain/inference/meta_reference/inference.py
View file

@ -77,7 +77,8 @@ class MetaReferenceInferenceImpl(Inference):
logprobs=logprobs,
)
return self._chat_completion(request)
async for chunk in self.chat_completion_impl(request):
yield chunk
async def chat_completion_impl(
self, request: ChatCompletionRequest