onnxruntime

115e4499 - [MLAS + CORE] Improve YOLOX FP32 models performance on CPU (#32335)

[MLAS + CORE] Improve YOLOX FP32 models performance on CPU (#32335) ### Description Extended ORT pattern matching to replace 6 Slice + 1 Concat with the existing SpaceToDepth operation, reducing operator overhead. ​ Convolution Load Balancing: Improved thread-wise distribution of convolution work to avoid uneven workloads and thread idle time, improving multi-thread performance​ Observation: YOLOX-Tiny gains ~16.8% at 2T and 15.4% at 4T, YOLOX-Nano gains ~8% at 2T and at 4T, while YOLOX-Small shows no difference​ <img width="489" height="262" alt="yolox" src="https://github.com/user-attachments/assets/e99f6cfb-74cc-4a75-bc87-d50051c147a9" /> --------- Co-authored-by: Manogna-Sree <elisetti.manognasree@multicorewareinc.com>