phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 10:39:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add version to REST API url

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-18 18:53:06 -08:00
parent 7693786322
commit c73fe390ad
18 changed files with 32837 additions and 6032 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/apis/batch_inference/batch_inference.py
View file

@ -49,7 +49,7 @@ class BatchChatCompletionResponse(BaseModel):
@runtime_checkable
class BatchInference(Protocol):
@webmethod(route="/batch_inference/completion")
@webmethod(route="/batch-inference/completion")
async def batch_completion(
self,
model: str,
@ -58,7 +58,7 @@ class BatchInference(Protocol):
logprobs: Optional[LogProbConfig] = None,
) -> BatchCompletionResponse: ...
@webmethod(route="/batch_inference/chat_completion")
@webmethod(route="/batch-inference/chat-completion")
async def batch_chat_completion(
self,
model: str,