ltqin fca34268d1 flashattention fwd add (80, 96) instance (#3415) ...

* add hdim (96,96) instance

* change to (80,96)

* format py

* remove 96 in optdim

* when N=6 change to llvm_amdgcn_raw_buffer_load_i32x3

[ROCm/composable_kernel commit: 92653168c2]

2025-12-17 09:16:11 -08:00

..

mma

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

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

amd_buffer_addressing_builtins.hpp

flashattention fwd add (80, 96) instance (#3415)

2025-12-17 09:16:11 -08:00

amd_buffer_addressing.hpp

flashattention fwd add (80, 96) instance (#3415)

2025-12-17 09:16:11 -08:00

amd_transpose_load_encoding.hpp

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

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

arch.hpp

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

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

generic_memory_space_atomic.hpp

Add validity checks for MoE FlatMM scatter and enable bf16 hardware atomic-add (#3236)

2025-11-28 09:43:01 +01:00

utility.hpp

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

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

workgroup_barrier.hpp

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

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