Commit 80197ca
File tree
342 files changed
+1027
-1
lines changed- client_example
- 01_gemm
- 02_gemm_add_add_fastgelu
- 03_gemm_layernorm
- 04_contraction
- 05_layernorm
- 06_softmax
- 07_grouped_convnd_fwd
- 08_fused_attention
- 09_quantization
- 10_grouped_convnd_bwd_data
- 11_grouped_conv_bwd_weight
- 12_elementwise_normalization
- 13_batchnorm
- 14_instance_id
- 15_convnd_bwd_data
- 16_convnd_fwd
- 17_grouped_gemm_fastgelu
- 18_groupnorm
- 19_pool
- 20_splitk_gemm
- 21_grouped_gemm_bias
- 22_grouped_gemm
- 23_elementwise_transpose
- 24_grouped_conv_activation
- 25_wrapper
- 26_reduce
- 27_im2col_col2im
- 28_gemm_mx
- 29_gemm_add_multiply
- 30_gemm_bf16Aint8B
- 31_grouped_gemm_bf16Aint8B
- codegen
- test
- rtc
- example
- 01_gemm
- 02_gemm_bilinear
- 03_gemm_bias_relu
- 04_gemm_add_add_fastgelu
- 09_convnd_fwd
- 10_convnd_fwd_multiple_d_multiple_reduce
- 12_reduce
- 13_pool2d_fwd
- 14_gemm_quantization
- 15_grouped_gemm
- 16_gemm_multi_d_multi_reduces
- 17_convnd_bwd_data
- 18_batched_gemm_reduce
- 19_binary_elementwise
- 20_grouped_conv_bwd_weight
- 21_gemm_layernorm
- 22_cgemm
- 23_softmax
- 24_batched_gemm
- 25_gemm_bias_e_permute
- 26_contraction
- 27_layernorm2d_fwd
- 28_grouped_gemm_bias_e_permute
- 29_batched_gemm_bias_e_permute
- 30_grouped_conv_fwd_multiple_d
- 31_batched_gemm_gemm
- 32_batched_gemm_scale_softmax_gemm
- 33_multiple_reduce
- 34_batchnorm
- 35_splitK_gemm
- 36_sparse_embedding
- 37_batched_gemm_add_add_relu_gemm_add
- 38_grouped_conv_bwd_data_multiple_d
- 39_permute
- 40_conv2d_fwd_quantization
- 41_grouped_conv_conv_fwd
- 42_groupnorm_fwd
- 43_splitk_gemm_bias_e_permute
- 44_elementwise_permute
- 45_elementwise_normalization
- 46_gemm_add_multiply
- 47_gemm_bias_softmax_gemm_permute
- 48_pool3d_fwd
- 49_maxpool2d_bwd
- 50_put_element
- 51_avgpool3d_bwd
- 52_im2col_col2im
- 53_layernorm2d_bwd
- 54_groupnorm_bwd
- 59_grouped_gemm_multi_ABD
- 60_gemm_multi_ABD
- 61_contraction_multi_ABD
- 62_convnd_activ
- binary
- convinvscale
- convscale_add
- convscale_reduce
- convscale_relu
- convscale
- dynamic_unary
- multi_AB
- unary
- 63_layernorm4d_fwd
- 64_fpAintB_gemm
- 65_gemm_multiply_multiply
- 66_complex_contraction_bilinear
- 67_gemm_microscaling
- 68_gemm_add
- 69_gemm_add_relu
- ck_tile
- 01_fmha
- 02_layernorm2d
- 03_gemm
- 04_img2col
- 05_reduce
- 06_permute
- 09_topk_softmax
- 10_rmsnorm2d
- 11_add_rmsnorm2d_rdquant
- 12_smoothquant
- 13_moe_sorting
- 14_moe_smoothquant
- 15_fused_moe
- 16_batched_gemm
- 17_grouped_gemm
- 18_flatmm
- 19_gemm_multi_d
- 20_grouped_convolution
- 21_elementwise
- 22_gemm_multi_abd
- 35_batched_transpose
- 36_pooling
- 38_block_scale_gemm
- 40_streamk_gemm
- 41_batched_contraction
- experimental/builder
- include/ck_tile/builder
- test
- library
- src
- tensor_operation_instance/gpu
- avg_pool2d_bwd
- avg_pool3d_bwd
- batched_gemm_add_relu_gemm_add
- batched_gemm_b_scale
- batched_gemm_bias_permute
- batched_gemm_gemm
- batched_gemm_multi_d
- batched_gemm_reduce
- batched_gemm_softmax_gemm_permute
- batched_gemm_softmax_gemm
- batched_gemm
- batchnorm
- column_to_image
- contraction_bilinear
- contraction_scale
- conv1d_bwd_data
- conv2d_bwd_data
- conv2d_fwd_bias_relu_add
- conv2d_fwd_bias_relu
- conv2d_fwd
- conv3d_bwd_data
- elementwise_normalization
- elementwise
- gemm_ab_scale
- gemm_add_add_fastgelu
- gemm_add_fastgelu
- gemm_add_multiply
- gemm_add_relu_add_layernorm
- gemm_add_relu
- gemm_add_silu
- gemm_add
- gemm_b_scale
- gemm_bias_add_reduce
- gemm_bilinear
- gemm_blockscale_wp
- gemm_fastgelu
- gemm_multi_abd
- gemm_multiply_add
- gemm_multiply_multiply_wp
- gemm_multiply_multiply
- gemm_mx
- gemm_reduce
- gemm_splitk
- gemm_streamk
- gemm_universal_batched
- gemm_universal_preshuffle
- gemm_universal_reduce
- gemm_universal_streamk
- gemm_universal
- gemm
- grouped_conv1d_bwd_weight
- grouped_conv1d_fwd
- grouped_conv2d_bwd_data
- grouped_conv2d_bwd_weight
- grouped_conv2d_fwd_bias_bnorm_clamp
- grouped_conv2d_fwd_bias_clamp
- grouped_conv2d_fwd_clamp
- grouped_conv2d_fwd_dynamic_op
- grouped_conv2d_fwd
- grouped_conv3d_bwd_data_bilinear
- grouped_conv3d_bwd_data_scale
- grouped_conv3d_bwd_data
- grouped_conv3d_bwd_weight_bilinear
- grouped_conv3d_bwd_weight_scale
- grouped_conv3d_bwd_weight
- grouped_conv3d_fwd_bias_bnorm_clamp
- grouped_conv3d_fwd_bias_clamp
- grouped_conv3d_fwd_bilinear
- grouped_conv3d_fwd_clamp
- grouped_conv3d_fwd_convinvscale
- grouped_conv3d_fwd_convscale_add
- grouped_conv3d_fwd_convscale_relu
- grouped_conv3d_fwd_convscale
- grouped_conv3d_fwd_dynamic_op
- grouped_conv3d_fwd_scaleadd_ab
- grouped_conv3d_fwd_scaleadd_scaleadd_relu
- grouped_conv3d_fwd_scale
- grouped_conv3d_fwd
- grouped_convnd_bwd_weight
- grouped_gemm_bias
- grouped_gemm_fastgelu
- grouped_gemm_fixed_nk_multi_abd
- grouped_gemm_fixed_nk
- grouped_gemm_tile_loop
- grouped_gemm
- image_to_column
- max_pool_bwd
- mha
- normalization_bwd_data
- normalization_bwd_gamma_beta
- normalization_fwd
- permute_scale
- pool2d_fwd
- pool3d_fwd
- quantization
- reduce
- softmax
- transpose
- utility
- profiler
- src
- test
- batched_gemm_b_scale
- batched_gemm_gemm
- batched_gemm_multi_d
- batched_gemm_reduce
- batched_gemm_softmax_gemm_permute
- batched_gemm_softmax_gemm
- batched_gemm
- batchnorm
- block_to_ctile_map
- ck_tile
- add_rmsnorm2d_rdquant
- atomic_add_op
- batched_gemm
- batched_transpose
- container
- core
- arch
- mma
- data_type
- elementwise
- epilogue
- fmha
- gemm_block_scale
- gemm_multi_abd
- gemm_multi_d
- gemm_streamk
- gemm_tile_engine
- gemm_weight_preshuffle
- gemm
- grouped_gemm_multi_d
- grouped_gemm_preshuffle
- grouped_gemm_quant
- grouped_gemm
- image_to_column
- layernorm2d
- memory_copy
- moe_smoothquant
- moe_sorting
- permute
- pooling
- reduce
- rmsnorm2d
- slice_tile
- smoothquant
- topk_softmax
- utility
- print
- contraction
- conv_tensor_rearrange
- conv_util
- convnd_bwd_data
- convnd_fwd
- data_type
- elementwise_normalization
- gemm_add
- gemm_b_scale
- gemm_blockscale_wp
- gemm_layernorm
- gemm_multi_abd
- gemm_multiply_multiply_wp
- gemm_mx
- gemm_reduce
- gemm_split_k
- gemm_universal_preshuffle
- gemm_universal_reduce
- gemm_universal_streamk
- gemm_universal
- gemm
- grouped_convnd_bwd_data
- grouped_convnd_bwd_weight
- grouped_convnd_fwd_activation
- grouped_convnd_fwd
- grouped_gemm
- magic_number_division
- mx_mfma_op
- normalization_bwd_data
- normalization_bwd_gamma_beta
- normalization_fwd
- permute_scale
- pool
- position_embedding
- quantization
- gemm
- reduce
- reference_conv_fwd
- s_prefetch_op
- scatter_gather
- smfmac_op
- softmax
- space_filling_curve
- transpose
- wmma_op
- wrapper
- tile_engine
- include
- ops
- gemm_multi_d
- gemm_preshuffle
- gemm
- tutorial
- ck_tile
- 00_copy_kernel
- 01_naive_gemm
Some content is hidden
Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.
342 files changed
+1027
-1
lines changed| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
| 1 | + | |
| 2 | + | |
| 3 | + | |
1 | 4 | | |
2 | 5 | | |
3 | 6 | | |
| |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
| 1 | + | |
| 2 | + | |
| 3 | + | |
1 | 4 | | |
2 | 5 | | |
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
| 1 | + | |
| 2 | + | |
| 3 | + | |
1 | 4 | | |
2 | 5 | | |
3 | 6 | | |
| |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
| 1 | + | |
| 2 | + | |
| 3 | + | |
1 | 4 | | |
2 | 5 | | |
3 | 6 | | |
| |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
| 1 | + | |
| 2 | + | |
| 3 | + | |
1 | 4 | | |
2 | 5 | | |
3 | 6 | | |
| |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
| 1 | + | |
| 2 | + | |
| 3 | + | |
1 | 4 | | |
2 | 5 | | |
3 | 6 | | |
| |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
| 1 | + | |
| 2 | + | |
| 3 | + | |
1 | 4 | | |
2 | 5 | | |
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
| 1 | + | |
| 2 | + | |
| 3 | + | |
1 | 4 | | |
2 | 5 | | |
3 | 6 | | |
| |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
| 1 | + | |
| 2 | + | |
| 3 | + | |
1 | 4 | | |
2 | 5 | | |
3 | 6 | | |
| |||
| Original file line number | Diff line number | Diff line change | |
|---|---|---|---|
| |||
| 1 | + | |
| 2 | + | |
| 3 | + | |
1 | 4 | | |
2 | 5 | | |
3 | 6 | | |
| |||
0 commit comments