ViperEkura 34471252ab perf: pipeline fp8 gemm fragment loads and pack bf16 epilogue ...

- software-pipeline A-fragment ldmatrix: row mt+1 loads hide behind row mt MMAs
- bf16 epilogue packs two columns into one bfloat162 store (half the stores)
- fp8 vs bf16 linear: fwd 1.15x@512, 1.5x@2048, 2.8x@4096; bwd up to 2.7x, peak 35 TFLOPS

2026-08-23 21:32:20 +08:00

..

common.h

perf: vectorize fp8 quantize and swizzle gemm smem

2026-08-23 20:31:44 +08:00

gemm.cuh

perf: pipeline fp8 gemm fragment loads and pack bf16 epilogue

2026-08-23 21:32:20 +08:00

ops.cu

perf: vectorize fp8 quantize and swizzle gemm smem

2026-08-23 20:31:44 +08:00