phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-05 04:17:32 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix agentic calling inference

Browse source
This commit is contained in:
Xi Yan 2024-09-11 18:30:09 -07:00
parent 2501b3d7de
commit f55ffa8b53
4 changed files with 8 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_toolchain/inference/meta_reference/inference.py
View file

@ -77,14 +77,6 @@ class MetaReferenceInferenceImpl(Inference):
logprobs=logprobs,
)
async for chunk in self.chat_completion_impl(request):
yield chunk
async def chat_completion_impl(
self, request: ChatCompletionRequest
) -> AsyncIterator[
Union[ChatCompletionResponseStreamChunk, ChatCompletionResponse]
]:
messages = prepare_messages(request)
model = resolve_model(request.model)
if model is None: