ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 10:09:41 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
377a3da125c74566ef48f45ddea53407937b7b33
composable_kernel/example/ck_tile
History
Aviral Goel 0fb1cfa4b7 fix(grouped_gemm): pipeline selection when tail_num varies per group and leads to numerical error (#2863) 
* fix(grouped_gemm): numerical errors on gfx950 by correctly calculating the tail num

* WIP: add temp config to stress test numerical error correction

* refactor: remove comments

[ROCm/composable_kernel commit: db79fad16f]
2025-09-16 18:43:19 -07:00
..
01_fmha
[CK_TILE] fix bug when iperm =0 in fmha fwd (#2820)
2025-09-16 15:07:10 +08:00
02_layernorm2d
[CK_TILE] Refine Generic2dBlockShape to fix ck_tile example 2,10,11,14 on rdna3 and 4 (#2795)
2025-09-10 08:29:20 +08:00
03_gemm
[CK TILE GEMM] set correct value to TiledMMAPermuteN_ (#2839)
2025-09-13 20:54:08 -07:00
04_img2col
invoke script directly (#2687)
2025-08-19 00:23:07 -07:00
05_reduce
[CK_TILE] fix example reduces, permute and elementwise on gfx11 & gfx12 (#2810)
2025-09-11 12:41:20 +08:00
06_permute
[CK_TILE] fix example reduces, permute and elementwise on gfx11 & gfx12 (#2810)
2025-09-11 12:41:20 +08:00
09_topk_softmax
Fix latest AITER failure and add more AITER tests in CK CI. (#2782)
2025-09-04 13:44:00 -07:00
10_rmsnorm2d
[CK_TILE] Refine Generic2dBlockShape to fix ck_tile example 2,10,11,14 on rdna3 and 4 (#2795)
2025-09-10 08:29:20 +08:00
11_add_rmsnorm2d_rdquant
[CK_TILE] Refine Generic2dBlockShape to fix ck_tile example 2,10,11,14 on rdna3 and 4 (#2795)
2025-09-10 08:29:20 +08:00
12_smoothquant
[CK_TILE] Refine Generic2dBlockShape to fix ck_tile example 2,10,11,14 on rdna3 and 4 (#2795)
2025-09-10 08:29:20 +08:00
13_moe_sorting
Fix latest AITER failure and add more AITER tests in CK CI. (#2782)
2025-09-04 13:44:00 -07:00
14_moe_smoothquant
[CK_TILE] Refine Generic2dBlockShape to fix ck_tile example 2,10,11,14 on rdna3 and 4 (#2795)
2025-09-10 08:29:20 +08:00
15_fused_moe
fix(copyright header): add header to missing files (#2807)
2025-09-11 12:27:08 -07:00
16_batched_gemm
[CK_TILE] Fix example batched_gemm, grouped_gemm, gemm_multi_d, convolution on gfx11 & gfx12 (#2808)
2025-09-11 07:27:33 -07:00
17_grouped_gemm
fix(grouped_gemm): pipeline selection when tail_num varies per group and leads to numerical error (#2863)
2025-09-16 18:43:19 -07:00
18_flatmm
[CK_TILE] Enable ck_tile tests on gfx11 and gfx12 (#2821)
2025-09-12 12:45:14 -07:00
19_gemm_multi_d
[CK_TILE] Fix example batched_gemm, grouped_gemm, gemm_multi_d, convolution on gfx11 & gfx12 (#2808)
2025-09-11 07:27:33 -07:00
20_grouped_convolution
[CK_TILE] Fix example batched_gemm, grouped_gemm, gemm_multi_d, convolution on gfx11 & gfx12 (#2808)
2025-09-11 07:27:33 -07:00
21_elementwise
[CK_TILE] fix example reduces, permute and elementwise on gfx11 & gfx12 (#2810)
2025-09-11 12:41:20 +08:00
35_batched_transpose
Fix latest AITER failure and add more AITER tests in CK CI. (#2782)
2025-09-04 13:44:00 -07:00
38_block_scale_gemm
[CK TILE GEMM] Fixed the regression issue with transpose C in Quant Gemm (#2819)
2025-09-11 11:38:16 -07:00
39_copy
fix(copyright header): add header to missing files (#2807)
2025-09-11 12:27:08 -07:00
CMakeLists.txt
feat(copy_kernel): add basic copy kernel example with beginner friendly documentation (#2582)
2025-08-11 10:54:37 -07:00
remod.py
upgrade from clang-format-12 to clang-format-18 (#2568)
2025-07-28 11:34:07 -07:00