cutlass/examples/41_fused_multi_head_attention
ANIKET SHIVAM 66d9cddc83
New updates for 2.11 (#775)
* New updates.

* Minor profiler updates

Co-authored-by: Aniket Shivam <ashivam@nvidia.com>
2023-01-20 16:32:57 -05:00
..
gemm New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
iterators New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
attention_scaling_coefs_updater.h New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
CMakeLists.txt New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
debug_utils.h New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
default_fmha_grouped.h New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
epilogue_pipelined.h New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
epilogue_rescale_output.h New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
epilogue_thread_apply_logsumexp.h New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
find_default_mma.h New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
fmha_grouped_problem_visitor.h New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
fmha_grouped.h New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
fused_multihead_attention_fixed_seqlen.cu New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
fused_multihead_attention_variable_seqlen.cu New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
gemm_kernel_utils.h New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
kernel_forward.h New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
mma_from_smem.h New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00