phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-10 11:39:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Remove request arg from chat completion response processing

Browse source 
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
This commit is contained in:
Yuan Tang 2024-10-11 16:18:40 -04:00
parent a2b87ed0cb
commit fe9029f169
No known key found for this signature in database
7 changed files with 14 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/adapters/inference/tgi/tgi.py
View file

@ -116,7 +116,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
response = OpenAICompatCompletionResponse(
choices=[choice],
)
return process_chat_completion_response(request, response, self.formatter)
return process_chat_completion_response(response, self.formatter)
async def _stream_chat_completion(
self, request: ChatCompletionRequest
@ -135,7 +135,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
stream = _generate_and_convert_to_openai_compat()
async for chunk in process_chat_completion_stream_response(
request, stream, self.formatter
stream, self.formatter
):
yield chunk