Files
mlx/mlx/backend/cuda/device.cpp
Cheng 65d0d40232 Split cuDNN helpers into a separate header (#2491)
* Add RAII managed CudaGraph class

* Implement forward rms_norm with cuDNN

* Revert back to old rms norm kernel
2025-08-20 09:29:28 +09:00

9.7 KiB