A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 17, 00:30 UTC
[Bugfix] Fix call to init_logger in openai server (#4765)
Nadav Shmayovits committed
Jun 1, 2024 at 20:18 UTC
37464a0f745a0204da7443d2a6ef4b8f65e5af12
1 file changed
+1
-1
vllm/entrypoints/openai/api_server.py
+1
-1
@@ -36,7 +36,7 @@ openai_serving_chat: OpenAIServingChat
36
openai_serving_completion: OpenAIServingCompletion
37
openai_serving_embedding: OpenAIServingEmbedding
38
39
-logger = init_logger(__name__)
39
+logger = init_logger('vllm.entrypoints.openai.api_server')
40
41
_running_tasks: Set[asyncio.Task] = set()
42