@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / c782195662
Fork 0

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: