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 16, 20:45 UTC
[Bugfix][Frontend] remove duplicate init logger (#6581)
Daniele committed
Jul 19, 2024 at 19:16 UTC
51f8aa90ad409cc77bfab208be7f5907bf7d5330
1 file changed
-1
vllm/entrypoints/openai/api_server.py
-1
@@ -42,7 +42,6 @@ from vllm.version import __version__ as VLLM_VERSION
42
43
TIMEOUT_KEEP_ALIVE = 5 # seconds
44
45
-logger = init_logger(__name__)
45
engine: AsyncLLMEngine
46
engine_args: AsyncEngineArgs
47
openai_serving_chat: OpenAIServingChat