ROCm/composable_kernel

mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-14 02:02:46 +00:00

Files

History

Illia Silin 8df9260b3e Add a daily CI build on gfx908. (#1987 )

* add one daily ci build on gfx908

* add redis invocation tag for gfx908

* make ci build for gfx908 conditional

* fix groovy logic

* add option to run perf tests for gfx908

* disable a few tests on mi100

[ROCm/composable_kernel commit: 1342ecf7fb]

2025-03-17 18:08:53 -07:00

..

Add a daily CI build on gfx908. (#1987 )

2025-03-17 18:08:53 -07:00

02_gemm_bilinear

…

03_gemm_bias_relu

…

04_gemm_add_add_fastgelu

remove support for gfx940 and gfx941 targets (#1944 )

2025-03-05 11:07:33 -08:00

Add a daily CI build on gfx908. (#1987 )

2025-03-17 18:08:53 -07:00

10_convnd_fwd_multiple_d_multiple_reduce

Fix example_convnd_fwd_max_xdl_int8 failures on MI300 (#1666 )

2024-11-14 08:40:50 -08:00

…

…

14_gemm_quantization

…

15_grouped_gemm

Async grouped gemm v3 (#1940 )

2025-03-17 16:42:43 +01:00

16_gemm_multi_d_multi_reduces

Fix example_convnd_fwd_max_xdl_int8 failures on MI300 (#1666 )

2024-11-14 08:40:50 -08:00

17_convnd_bwd_data

…

18_batched_gemm_reduce

remove support for gfx940 and gfx941 targets (#1944 )

2025-03-05 11:07:33 -08:00

19_binary_elementwise

…

20_grouped_conv_bwd_weight

Apply universal gemm to bwd_weight_cshuffle operator (#1873 )

2025-02-18 10:10:22 +01:00

21_gemm_layernorm

OCP FP8 support for gfx12. (#1710 )

2024-12-03 08:42:55 -08:00

…

…

24_batched_gemm

Added Int4 mixed batch gemm support (#1839 )

2025-02-10 11:17:02 +08:00

25_gemm_bias_e_permute

…

…

27_layernorm2d_fwd

…

28_grouped_gemm_bias_e_permute

…

29_batched_gemm_bias_e_permute

…

30_grouped_conv_fwd_multiple_d

Remove CK_USE_AMD_MFMA_GFX950 (#1935 )

2025-03-04 10:32:25 -08:00

31_batched_gemm_gemm

Merge from internal (#1857 )

2025-02-07 15:05:05 -07:00

32_batched_gemm_scale_softmax_gemm

OCP FP8 support for gfx12. (#1710 )

2024-12-03 08:42:55 -08:00

33_multiple_reduce

…

…

OCP FP8 support for gfx12. (#1710 )

2024-12-03 08:42:55 -08:00

36_sparse_embedding

…

37_batched_gemm_add_add_relu_gemm_add

OCP FP8 support for gfx12. (#1710 )

2024-12-03 08:42:55 -08:00

38_grouped_conv_bwd_data_multiple_d

OCP FP8 support for gfx12. (#1710 )

2024-12-03 08:42:55 -08:00

…

40_conv2d_fwd_quantization

…

41_grouped_conv_conv_fwd

Merge from internal (#1857 )

2025-02-07 15:05:05 -07:00

42_groupnorm_fwd

…

43_splitk_gemm_bias_e_permute

…

44_elementwise_permute

Prevent instantiation of undefined FP8 operators. (#1639 )

2024-11-05 13:58:29 -08:00

45_elementwise_normalization

…

46_gemm_add_multiply

…

47_gemm_bias_softmax_gemm_permute

OCP FP8 support for gfx12. (#1710 )

2024-12-03 08:42:55 -08:00

…

49_maxpool2d_bwd

…

…

51_avgpool3d_bwd

…

52_im2col_col2im

…

53_layernorm2d_bwd

…

54_groupnorm_bwd

…

59_grouped_gemm_multi_ABD

OCP FP8 support for gfx12. (#1710 )

2024-12-03 08:42:55 -08:00

60_gemm_multi_ABD

…

61_contraction_multi_ABD

…

62_convnd_activ

remove support for gfx940 and gfx941 targets (#1944 )

2025-03-05 11:07:33 -08:00

63_layernorm4d_fwd

…

64_fpAintB_gemm

…

65_gemm_multiply_multiply

[Block Scale GEMM] Optimized block scale gemm (#1950 )

2025-03-11 10:11:21 -07:00

66_complex_contraction_bilinear

update layernorm (#1570 )

2024-10-22 09:26:18 +08:00

67_gemm_microscaling

Fix for Unsupported Input Shapes/Sizes in Stream-K GEMM - BF16/FP16 (#1866 )

2025-02-18 08:46:47 -08:00

hotfix fmoe build issue (#1976 )

2025-03-13 15:11:59 +08:00

CMakeLists.txt

disable tests that take too long to build for gfx90a (#1975 )

2025-03-12 17:54:03 -07:00

README.md

Add basic documentation structure (#1715 )

2024-12-04 00:46:47 +01:00

README.md

Back to the main page

Composable Kernel examples