phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 19:04:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix vLLM adapter chat_completion signature

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-01 13:09:03 -07:00
parent adecb2a2d3
commit bf4f97a2e1
1 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -75,7 +75,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
for model in self.client.models.list()
]
def completion(
async def completion(
self,
model: str,
content: InterleavedTextMedia,
@ -86,7 +86,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
) -> Union[CompletionResponse, CompletionResponseStreamChunk]:
raise NotImplementedError()
def chat_completion(
async def chat_completion(
self,
model: str,
messages: List[Message],
@ -111,7 +111,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
if stream:
return self._stream_chat_completion(request, self.client)
else:
return self._nonstream_chat_completion(request, self.client)
return await self._nonstream_chat_completion(request, self.client)
async def _nonstream_chat_completion(
self, request: ChatCompletionRequest, client: OpenAI