phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 16:09:53 +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/impls/vllm/vllm.py
View file

@ -134,7 +134,7 @@ class VLLMInferenceImpl(ModelRegistryHelper, Inference):
if self.engine:
self.engine.shutdown_background_loop()
def completion(
async def completion(
self,
model: str,
content: InterleavedTextMedia,
@ -152,7 +152,7 @@ class VLLMInferenceImpl(ModelRegistryHelper, Inference):
logprobs=logprobs,
)
def chat_completion(
async def chat_completion(
self,
model: str,
messages: list[Message],
@ -189,7 +189,7 @@ class VLLMInferenceImpl(ModelRegistryHelper, Inference):
if stream:
return self._stream_chat_completion(request, results_generator)
else:
return self._nonstream_chat_completion(request, results_generator)
return await self._nonstream_chat_completion(request, results_generator)
async def _nonstream_chat_completion(
self, request: ChatCompletionRequest, results_generator: AsyncGenerator