GOATnote

Add high-performance sparse BSR GEMM for Ada (sm_89) - 1.74× vs baseline

2

Performance: - 52.1 TFLOPS on NVIDIA L4 (Ada, SM 8.9) - 1.74× faster than CUTLASS 4.3.0 baseline (~30 TFLOPS) - 63× faster than cuSPARSE (0.87 TFLOPS) - 83% efficiency vs...