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 15, 03:30 UTC
[Misc] remove unused jinaai_serving_reranking (#18878)
Signed-off-by: Abirdcfly <fp544037857@gmail.com>
Abirdcfly committed
Jul 7, 2025 at 17:14 UTC
448acad31eae34508a7e0ed0877b95dad8df8bb9
1 file changed
-5
vllm/entrypoints/openai/api_server.py
-5
@@ -1409,11 +1409,6 @@ async def init_app_state(
1409
1410
enable_serving_reranking = (model_config.task == "classify" and getattr(
1411
model_config.hf_config, "num_labels", 0) == 1)
1412
- state.jinaai_serving_reranking = ServingScores(
1413
- engine_client,
1414
- model_config,
1415
- state.openai_serving_models,
1416
- request_logger=request_logger) if enable_serving_reranking else None
1412
state.openai_serving_scores = ServingScores(
1413
engine_client,
1414
model_config,