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, 00:45 UTC
Replace missed warning_once for rerank API (#12472)
Signed-off-by: mgoin <michael@neuralmagic.com>
Michael Goin committed
Jan 28, 2025 at 14:06 UTC
0f657bdc52d4ad1d079beddf8e7556c419aca7b4
1 file changed
+1
-1
vllm/entrypoints/openai/api_server.py
+1
-1
@@ -528,7 +528,7 @@ async def do_rerank(request: RerankRequest, raw_request: Request):
528
@router.post("/v1/rerank")
529
@with_cancellation
530
async def do_rerank_v1(request: RerankRequest, raw_request: Request):
531
- logger.warning(
531
+ logger.warning_once(
532
"To indicate that the rerank API is not part of the standard OpenAI"
533
" API, we have located it at `/rerank`. Please update your client"
534
"accordingly. (Note: Conforms to JinaAI rerank API)")