phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-16 11:12:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Make all API methods async def again

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-18 16:50:57 -07:00
parent 95a96afe34
commit 627edaf407
17 changed files with 120 additions and 145 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/adapters/inference/tgi/tgi.py
View file

@ -66,7 +66,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
async def shutdown(self) -> None:
pass
def completion(
async def completion(
self,
model: str,
content: InterleavedTextMedia,
@ -76,7 +76,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
) -> AsyncGenerator:
raise NotImplementedError()
def chat_completion(
async def chat_completion(
self,
model: str,
messages: List[Message],
@ -101,7 +101,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
if stream:
return self._stream_chat_completion(request)
else:
return self._nonstream_chat_completion(request)
return await self._nonstream_chat_completion(request)
async def _nonstream_chat_completion(
self, request: ChatCompletionRequest