Necofish e7221180e1 [Kernel] Optimize SM120 CUTLASS blockwise FP8 GEMM (#37970) ...

Signed-off-by: Necofish <liuxiangyang@mail.ustc.edu.cn>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

2026-03-25 08:20:04 -07:00

..

cutlass_gemm_caller.cuh

…

scaled_mm_azp_sm90_int8.cu

…

scaled_mm_blockwise_sm90_fp8_dispatch.cuh

…

scaled_mm_blockwise_sm90_fp8.cu

…

scaled_mm_blockwise_sm100_fp8_dispatch.cuh

fix cutlass_3x_gemm_fp8_blockwise on sm103a (#32224)

2026-02-02 11:47:46 -08:00

scaled_mm_blockwise_sm100_fp8.cu

…

scaled_mm_blockwise_sm120_fp8_dispatch.cuh

[Kernel] Optimize SM120 CUTLASS blockwise FP8 GEMM (#37970)

2026-03-25 08:20:04 -07:00

scaled_mm_blockwise_sm120_fp8.cu

…

scaled_mm_helper.hpp

…

scaled_mm_kernels.hpp

…

scaled_mm_sm90_fp8_dispatch.cuh

[kernel] Improve FP8 PTPC on Hopper for larger shapes (#28692)

2025-11-14 09:59:11 -08:00

scaled_mm_sm90_fp8.cu

…

scaled_mm_sm90_int8_dispatch.cuh

…

scaled_mm_sm90_int8.cu

…

scaled_mm_sm100_fp8_dispatch.cuh

fix cutlass_3x_gemm_fp8_blockwise on sm103a (#32224)

2026-02-02 11:47:46 -08:00

scaled_mm_sm100_fp8.cu

…

scaled_mm_sm120_fp8_dispatch.cuh

[Perf] Optimize FP8 gemm of sm120. (#34424)

2026-02-24 22:25:24 -08:00

scaled_mm_sm120_fp8.cu

…

scaled_mm.cuh

fix cutlass_3x_gemm_fp8_blockwise on sm103a (#32224)

2026-02-02 11:47:46 -08:00