onnxruntime
16ae99ed - Add cuda graph implementation for NV TRT RTX EP (#25787)

Commit
194 days ago
Add cuda graph implementation for NV TRT RTX EP (#25787) ### Description This change adds CUDA Graph support to the NV TensorRT RTX Execution Provider (EP). ### Motivation and Context Integrating CUDA Graphs into the NV TRT RTX EP provides: Lower latency by minimizing per-kernel launch overhead. Better throughput for repeated inference runs. Improved efficiency on GPUs with high kernel launches overhead sensitivity. --------- Co-authored-by: Maximilian Mueller <maximilianm@nvidia.com> Co-authored-by: Gaurav Garg <gaugarg@nvidia.com>
Author
Parents
Loading