Illia Silin d80f50d5e9 fix clang format (#1662) ...

[ROCm/composable_kernel commit: efd9261545]

2024-11-13 09:20:18 -08:00

..

impl

fix clang format (#1662)

2024-11-13 09:20:18 -08:00

conv_tensor_rearrange_op.hpp

…

convolution_backward_data_specialization.hpp

…

convolution_backward_weight_specialization.hpp

…

convolution_forward_specialization.hpp

…

device_avgpool_bwd.hpp

…

device_base.hpp

…

device_batched_contraction_multiple_d.hpp

…

device_batched_gemm_e_permute.hpp

…

device_batched_gemm_gemm.hpp

…

device_batched_gemm_multi_d.hpp

…

device_batched_gemm_multiple_d_gemm_multiple_d.hpp

…

device_batched_gemm_softmax_gemm_permute.hpp

…

device_batched_gemm_softmax_gemm.hpp

…

device_batched_gemm.hpp

…

device_batchnorm_backward.hpp

…

device_batchnorm_forward.hpp

…

device_batchnorm_infer.hpp

…

device_cgemm.hpp

Implement GetWorkSpaceSize from BaseOperator. (#1564)

2024-10-12 14:05:11 +08:00

device_contraction_multiple_abd.hpp

…

device_contraction_multiple_d.hpp

…

device_conv_bwd_data.hpp

…

device_conv_fwd_bias_activation_add.hpp

…

device_conv_fwd_bias_activation.hpp

…

device_conv_fwd.hpp

…

device_conv_tensor_rearrange.hpp

…

device_elementwise_normalization.hpp

…

device_elementwise_scale.hpp

…

device_elementwise.hpp

…

device_gemm_bias_e_permute.hpp

…

device_gemm_dequantB.hpp

…

device_gemm_multiple_abd.hpp

…

device_gemm_multiple_d_ab_scale.hpp

[GEMM] F8 GEMM, performance optimized. (#1384)

2024-07-19 22:06:52 +08:00

device_gemm_multiple_d_layernorm.hpp

…

device_gemm_multiple_d_multiple_r.hpp

…

device_gemm_multiple_d.hpp

[GEMM] gemm_universal related optimization (#1453)

2024-08-14 10:42:30 +08:00

device_gemm_reduce.hpp

…

device_gemm_splitk.hpp

…

device_gemm_streamk_v2.hpp

…

device_gemm_streamk.hpp

…

device_gemm_v2.hpp

Universal gemm splitk using reduce (with multi-d) (#1341)

2024-07-19 22:01:22 +08:00

device_gemm.hpp

…

device_grouped_contraction_multiple_d.hpp

…

device_grouped_conv_bwd_data_multiple_d.hpp

…

device_grouped_conv_bwd_weight_multiple_d.hpp

…

device_grouped_conv_bwd_weight.hpp

…

device_grouped_conv_fwd_multiple_abd.hpp

Add Grouped Conv Fwd Large Tensor kernel (#1432)

2024-08-06 10:06:10 +02:00

device_grouped_conv_fwd_multiple_d.hpp

…

device_grouped_conv_fwd.hpp

…

device_grouped_gemm_fixed_nk.hpp

…

device_grouped_gemm_multi_abd_fixed_nk.hpp

…

device_grouped_gemm_multi_abd.hpp

…

device_grouped_gemm_multiple_d_splitk.hpp

…

device_grouped_gemm_softmax_gemm_permute.hpp

…

device_grouped_gemm_splitk.hpp

…

device_grouped_gemm_tile_loop.hpp

…

device_grouped_gemm.hpp

…

device_max_pool_bwd.hpp

…

device_multiple_reduce.hpp

…

device_normalization_bwd_data.hpp

…

device_normalization_bwd_gamma_beta.hpp

…

device_normalization_fwd.hpp

…

device_permute.hpp

…

device_pool_fwd.hpp

…

device_put_element.hpp

…

device_reduce_multi_d.hpp

Universal gemm splitk using reduce (with multi-d) (#1341)

2024-07-19 22:01:22 +08:00

device_reduce.hpp

…

device_softmax.hpp

…

device_splitk_contraction_multiple_d.hpp

…

gemm_specialization.hpp

…

helper.hpp

Refactor transform conv to gemm fwd (#1391)

2024-07-19 09:29:25 +02:00

masking_specialization.hpp

…

matrix_padder.hpp

…

reduction_operator_mapping.hpp

…

tensor_layout.hpp

Add support for NGCHW in grouped conv bwd wei (#1491)

2024-09-03 10:52:03 +02:00

tensor_specialization.hpp

…

welford_helper.hpp

…