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

update batch completion endpoint

Browse source
This commit is contained in:
Ashwin Bharambe 2024-07-22 16:08:28 -07:00
parent 1e573843ce
commit 9b51b4edd8
2 changed files with 31 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_toolchain/inference/api/endpoints.py
View file

@ -108,10 +108,10 @@ class Inference(Protocol):
async def batch_completion(
self,
request: BatchCompletionRequest,
) -> List[CompletionResponse]: ...
) -> BatchCompletionResponse: ...
@webmethod(route="/inference/batch_chat_completion")
async def batch_chat_completion(
self,
request: BatchChatCompletionRequest,
) -> List[ChatCompletionResponse]: ...
) -> BatchChatCompletionResponse: ...