ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-16 02:54:21 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
be39c00a8e4f9716b0242fb16ac922cff5834805
composable_kernel/include/ck_tile/ops/gemm/block
History
asleepzzz 4730050182 Revert "Optimize fmha fwd decode & prefill for gfx950 (#2641)" (#2670) 
This reverts commit 747d127983.

[ROCm/composable_kernel commit: 5b39de4bb6]
2025-08-12 20:27:10 +08:00
..
block_gemm_areg_bgmem_creg_v1_default_policy.hpp
CK Tile FA Training kernels (#1286)
2024-06-04 13:12:45 -05:00
block_gemm_areg_bgmem_creg_v1.hpp
[CK-Tile] Universal gemm memory bound pipeline (#1558)
2024-10-30 10:05:15 +01:00
block_gemm_areg_breg_creg_v1_custom_policy.hpp
[CK_TILE] FA bwd kernels optimization (#1397)
2024-08-16 13:40:10 -07:00
block_gemm_areg_breg_creg_v1_default_policy.hpp
[CK_TILE] FA bwd kernels optimization (#1397)
2024-08-16 13:40:10 -07:00
block_gemm_areg_breg_creg_v1.hpp
Revert "Optimize fmha fwd decode & prefill for gfx950 (#2641)" (#2670)
2025-08-12 20:27:10 +08:00
block_gemm_areg_bsmem_creg_one_warp_v1.hpp
[CK_TILE] Add fmha fwd N-Warp S-Shuffle pipeline (fmha fwd splitkv pipeline variant) (#1705)
2024-12-20 14:41:01 +08:00
block_gemm_areg_bsmem_creg_v1_custom_policy.hpp
CK Tile FA Training kernels (#1286)
2024-06-04 13:12:45 -05:00
block_gemm_areg_bsmem_creg_v1_default_policy.hpp
CK Tile FA Training kernels (#1286)
2024-06-04 13:12:45 -05:00
block_gemm_areg_bsmem_creg_v1.hpp
[CK_TILE] More fmha splitkv optimizations (#1588)
2024-10-26 18:35:45 +08:00
block_gemm_areg_bsmem_creg_v2_custom_policy.hpp
CK Tile FA Training kernels (#1286)
2024-06-04 13:12:45 -05:00
block_gemm_areg_bsmem_creg_v2_default_policy.hpp
CK Tile FA Training kernels (#1286)
2024-06-04 13:12:45 -05:00
block_gemm_areg_bsmem_creg_v2.hpp
[CK_TILE] Add fmha fwd N-Warp S-Shuffle pipeline (fmha fwd splitkv pipeline variant) (#1705)
2024-12-20 14:41:01 +08:00
block_gemm_areg_bsmem_creg_v2r1.hpp
ck tile pagedkv prefill (#2405)
2025-07-07 16:16:54 +08:00
block_gemm_asmem_breg_creg_v1_custom_policy.hpp
CK Tile FA Training kernels (#1286)
2024-06-04 13:12:45 -05:00
block_gemm_asmem_breg_creg_v1_default_policy.hpp
CK Tile FA Training kernels (#1286)
2024-06-04 13:12:45 -05:00
block_gemm_asmem_breg_creg_v1.hpp
[CK_TILE] More fmha splitkv optimizations (#1588)
2024-10-26 18:35:45 +08:00
block_gemm_asmem_bsmem_creg_v1_custom_policy.hpp
CK Tile FA Training kernels (#1286)
2024-06-04 13:12:45 -05:00
block_gemm_asmem_bsmem_creg_v1_default_policy.hpp
[CK_TILE] Fix tile_example_moe_sorting broke in #2436 (#2525)
2025-07-17 22:50:58 -07:00
block_gemm_asmem_bsmem_creg_v1.hpp
[CK-Tile] Universal gemm memory bound pipeline (#1558)
2024-10-30 10:05:15 +01:00
block_gemm_problem.hpp
Revert "Optimize fmha fwd decode & prefill for gfx950 (#2641)" (#2670)
2025-08-12 20:27:10 +08:00
block_universal_gemm_as_bs_cr.hpp
[CK_TILE] Use read_tr in universal gemm (#2436)
2025-07-16 23:56:22 -07:00
block_wp_asmem_bsmem_creg_v1_custom_policy.hpp
Merge flatmm Operator with universal gemm (#2434)
2025-07-11 08:27:55 -07:00
block_wp_asmem_bsmem_creg_v1.hpp
Merge flatmm Operator with universal gemm (#2434)
2025-07-11 08:27:55 -07:00