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, 06:45 UTC
Disable Logs Requests should Disable Logging of requests. (#1779)
Co-authored-by: Michael McCulloch <mjm.gitlab@fastmail.com>
Michael McCulloch committed
Nov 29, 2023 at 22:50 UTC
c782195662bd0beee20eef3f9d630379eff1415a
1 file changed
-2
vllm/entrypoints/openai/api_server.py
-2
@@ -207,7 +207,6 @@ async def create_chat_completion(request: ChatCompletionRequest,
207
- function_call (Users should implement this by themselves)
208
- logit_bias (to be supported by vLLM engine)
209
"""
210
- logger.info(f"Received chat completion request: {request}")
210
211
error_check_ret = await check_model(request)
212
if error_check_ret is not None:
@@ -386,7 +385,6 @@ async def create_completion(request: CompletionRequest, raw_request: Request):
385
suffix)
386
- logit_bias (to be supported by vLLM engine)
387
"""
389
- logger.info(f"Received completion request: {request}")
388
389
error_check_ret = await check_model(request)
390
if error_check_ret is not None: