| .. |
|
01_gemm
|
.
|
2025-09-20 16:09:34 +08:00 |
|
02_gemm_bilinear
|
.
|
2025-09-20 16:09:34 +08:00 |
|
03_gemm_bias_relu
|
.
|
2025-09-20 16:09:34 +08:00 |
|
04_gemm_add_add_fastgelu
|
.
|
2025-09-20 16:09:34 +08:00 |
|
09_convnd_fwd
|
.
|
2025-09-20 16:09:34 +08:00 |
|
10_convnd_fwd_multiple_d_multiple_reduce
|
.
|
2025-09-20 16:09:34 +08:00 |
|
12_reduce
|
.
|
2025-09-20 16:09:34 +08:00 |
|
13_pool2d_fwd
|
.
|
2025-09-20 16:09:34 +08:00 |
|
14_gemm_quantization
|
.
|
2025-09-20 16:09:34 +08:00 |
|
15_grouped_gemm
|
.
|
2025-09-20 16:09:34 +08:00 |
|
16_gemm_multi_d_multi_reduces
|
.
|
2025-09-20 16:09:34 +08:00 |
|
17_convnd_bwd_data
|
.
|
2025-09-20 16:09:34 +08:00 |
|
18_batched_gemm_reduce
|
.
|
2025-09-20 16:09:34 +08:00 |
|
19_binary_elementwise
|
.
|
2025-09-20 16:09:34 +08:00 |
|
20_grouped_conv_bwd_weight
|
.
|
2025-09-20 16:09:34 +08:00 |
|
21_gemm_layernorm
|
.
|
2025-09-20 16:09:34 +08:00 |
|
22_cgemm
|
.
|
2025-09-20 16:09:34 +08:00 |
|
23_softmax
|
.
|
2025-09-20 16:09:34 +08:00 |
|
24_batched_gemm
|
.
|
2025-09-20 16:09:34 +08:00 |
|
25_gemm_bias_e_permute
|
.
|
2025-09-20 16:09:34 +08:00 |
|
26_contraction
|
.
|
2025-09-20 16:09:34 +08:00 |
|
27_layernorm2d_fwd
|
.
|
2025-09-20 16:09:34 +08:00 |
|
28_grouped_gemm_bias_e_permute
|
.
|
2025-09-20 16:09:34 +08:00 |
|
29_batched_gemm_bias_e_permute
|
.
|
2025-09-20 16:09:34 +08:00 |
|
30_grouped_conv_fwd_multiple_d
|
.
|
2025-09-20 16:09:34 +08:00 |
|
31_batched_gemm_gemm
|
.
|
2025-09-20 16:09:34 +08:00 |
|
32_batched_gemm_scale_softmax_gemm
|
.
|
2025-09-20 16:09:34 +08:00 |
|
33_multiple_reduce
|
.
|
2025-09-20 16:09:34 +08:00 |
|
34_batchnorm
|
.
|
2025-09-20 16:09:34 +08:00 |
|
35_splitK_gemm
|
.
|
2025-09-20 16:09:34 +08:00 |
|
36_sparse_embedding
|
.
|
2025-09-20 16:09:34 +08:00 |
|
37_batched_gemm_add_add_relu_gemm_add
|
.
|
2025-09-20 16:09:34 +08:00 |
|
38_grouped_conv_bwd_data_multiple_d
|
.
|
2025-09-20 16:09:34 +08:00 |
|
39_permute
|
.
|
2025-09-20 16:09:34 +08:00 |
|
40_conv2d_fwd_quantization
|
.
|
2025-09-20 16:09:34 +08:00 |
|
41_grouped_conv_conv_fwd
|
.
|
2025-09-20 16:09:34 +08:00 |
|
42_groupnorm_fwd
|
.
|
2025-09-20 16:09:34 +08:00 |
|
43_splitk_gemm_bias_e_permute
|
.
|
2025-09-20 16:09:34 +08:00 |
|
44_elementwise_permute
|
.
|
2025-09-20 16:09:34 +08:00 |
|
45_elementwise_normalization
|
.
|
2025-09-20 16:09:34 +08:00 |
|
46_gemm_add_multiply
|
.
|
2025-09-20 16:09:34 +08:00 |
|
47_gemm_bias_softmax_gemm_permute
|
.
|
2025-09-20 16:09:34 +08:00 |
|
48_pool3d_fwd
|
.
|
2025-09-20 16:09:34 +08:00 |
|
49_maxpool2d_bwd
|
.
|
2025-09-20 16:09:34 +08:00 |
|
50_put_element
|
.
|
2025-09-20 16:09:34 +08:00 |
|
51_avgpool3d_bwd
|
.
|
2025-09-20 16:09:34 +08:00 |
|
52_im2col_col2im
|
.
|
2025-09-20 16:09:34 +08:00 |
|
53_layernorm2d_bwd
|
.
|
2025-09-20 16:09:34 +08:00 |
|
54_groupnorm_bwd
|
.
|
2025-09-20 16:09:34 +08:00 |
|
59_grouped_gemm_multi_ABD
|
.
|
2025-09-20 16:09:34 +08:00 |
|
60_gemm_multi_ABD
|
.
|
2025-09-20 16:09:34 +08:00 |
|
61_contraction_multi_ABD
|
.
|
2025-09-20 16:09:34 +08:00 |
|
62_convnd_activ
|
.
|
2025-09-20 16:09:34 +08:00 |
|
63_layernorm4d_fwd
|
.
|
2025-09-20 16:09:34 +08:00 |
|
64_fpAintB_gemm
|
.
|
2025-09-20 16:09:34 +08:00 |
|
65_gemm_multiply_multiply
|
.
|
2025-09-20 16:09:34 +08:00 |
|
66_complex_contraction_bilinear
|
.
|
2025-09-20 16:09:34 +08:00 |
|
67_gemm_microscaling
|
.
|
2025-09-20 16:09:34 +08:00 |
|
ck_tile
|
.
|
2025-09-20 16:09:34 +08:00 |
|
CMakeLists.txt
|
.
|
2025-09-20 16:09:34 +08:00 |
|
README.md
|
.
|
2025-09-20 16:09:34 +08:00 |