ZheWang e6bcd192d4 Mx fp6 flatmm (#3601) ...

* add fp6 data-type and support sync/async dwordx3 load/store

* clang-format

* pre-commit

* 1st commit

* default mnk pass ut

* fix a distrubution

* fix

* fix bdram distr

* update

* pass ut

* improve perf

* update

* clean code

* resolve copilot comment

* reslove comment

* clang-format

---------

Co-authored-by: ZheWang <zhewan@amd.com>

2026-02-02 16:04:40 +08:00

..

reference_batched_contraction.hpp

[CK Tile] batched contraction kernel generalizing (#3126)

2025-12-02 13:30:27 +01:00

reference_batched_dropout_randval.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_batched_dropout.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_batched_elementwise.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_batched_gemm.hpp

Revert "Revert " Fp8 block scale quantization for fmha fwd (#3330)" (#3633)" (#3635)

2026-01-23 09:03:22 -08:00

reference_batched_masking.hpp

Add attention sink support for FMHA FWD (#3368)

2025-12-15 12:21:59 +08:00

reference_batched_rotary_position_embedding.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_batched_softmax.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_batched_transpose.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_blocked_attention.hpp

[CK_TILE][FMHA] Add sparse attention VSA (#3341)

2026-01-31 00:59:47 +08:00

reference_elementwise.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_fused_moe.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_gemm.hpp

Mx fp6 flatmm (#3601)

2026-02-02 16:04:40 +08:00

reference_grouped_conv_bwd_data.hpp

Update unsigned long literals and format specifiers to work correctly in Windows (#3483)

2026-01-02 22:16:41 -07:00

reference_grouped_conv_bwd_weight.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_grouped_conv_fwd.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_im2col.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_layernorm2d_fwd.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_moe_gemm.hpp

[CK_TILE] support split-k a16w4 gemm1 (#3389)

2025-12-29 23:05:35 +08:00

reference_moe_sorting.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_permute.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_pool.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_reduce.hpp

Dlejeune/ck tile 2d multiple reductions (#3147)

2026-01-09 11:16:37 +01:00

reference_rmsnorm2d_fwd.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_rowwise_quantization2d.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_softmax.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_topk.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00

reference_transpose.hpp

chore(copyright): update copyright header for include directory (#3293)

2025-11-26 11:00:05 -07:00