Ray Wang ec5e9ed0b8 Fix SM90 MQA logits (#229)

2025-11-19 10:50:36 +08:00

..

epilogue.hpp

Make various updates and fixes (#198)

2025-09-25 16:19:07 +08:00

runtime_utils.hpp

Fix old CUDA compatibility

2025-10-01 20:29:15 +08:00

sm90_bf16_gemm.hpp

Make various updates and fixes (#198)

2025-09-25 16:19:07 +08:00

sm90_bmk_bnk_mn.hpp

Make various updates and fixes (#198)

2025-09-25 16:19:07 +08:00

sm90_fp8_gemm_1d1d.hpp

Make various updates and fixes (#198)

2025-09-25 16:19:07 +08:00

sm90_fp8_gemm_1d2d.hpp

Make various updates and fixes (#198)

2025-09-25 16:19:07 +08:00

sm100_bf16_gemm.hpp

Make various updates and fixes (#198)

2025-09-25 16:19:07 +08:00

sm100_bmk_bnk_mn.hpp

Make various updates and fixes (#198)

2025-09-25 16:19:07 +08:00

sm100_fp8_gemm_1d1d.hpp

Make various updates and fixes (#198)

2025-09-25 16:19:07 +08:00

sm100_fp8_gemm_1d2d.hpp

Make various updates and fixes (#198)

2025-09-25 16:19:07 +08:00

smxx_clean_logits.hpp

Add SM90 kernels (#200)

2025-09-29 17:00:23 +08:00

smxx_cublaslt.hpp

Make various updates and fixes (#198)

2025-09-25 16:19:07 +08:00

smxx_fp8_mqa_logits.hpp

Fix SM90 MQA logits (#229)

2025-11-19 10:50:36 +08:00

smxx_fp8_paged_mqa_logits.hpp

Add SM100 kernels (#201)

2025-09-29 17:07:28 +08:00

smxx_layout.hpp

Make various updates and fixes: (#164)

2025-08-15 18:32:35 +08:00