phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

migrate agentic system

Browse source
This commit is contained in:
Xi Yan 2024-09-11 13:57:39 -07:00
parent 4b34f741d0
commit 6049aada71
5 changed files with 39 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_toolchain/inference/meta_reference/inference.py
View file

@ -77,6 +77,13 @@ class MetaReferenceInferenceImpl(Inference):
logprobs=logprobs,
)
return self._chat_completion(request)
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: