Files
WeKnora/rerank_server_demo.py
Suroy 5c6b710bae Update rerank_server_demo.py
1. Added CUDA debugging support
2. Improved memory management during model inference.
3. Fixed logits output

Test Device: Windows WSL Ubuntu 20.04 (python3.10 CUDA 5090 32G)
2026-03-18 18:25:05 +08:00

4.1 KiB