squall/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
9b8166e3f0
cutlass/examples/41_fused_multi_head_attention
History
dan_the_3rd 9b8166e3f0
fMHA: Add backward pass (#844) 
* fMHA: Add backward pass

* Better checks for strides/alignments

* Remove fb-internal URL

* torch.Tensor.untyped_storage requires pytorch 2.0+

* minor changes

* make test

---------

Co-authored-by: danthe3rd <danthe3rd>
Co-authored-by: Haicheng Wu <haichengw@nvidia.com>
2023-04-06 20:44:58 -04:00
..
epilogue fMHA: Sync FW with xFormers (#828) 2023-02-22 23:25:31 -05:00
gemm fMHA: Add backward pass (#844) 2023-04-06 20:44:58 -04:00
iterators Fix typos 2 (#842) 2023-03-09 23:22:56 -05:00
transform fMHA: Sync FW with xFormers (#828) 2023-02-22 23:25:31 -05:00
CMakeLists.txt fMHA: Add backward pass (#844) 2023-04-06 20:44:58 -04:00
debug_utils.h fMHA: Sync FW with xFormers (#828) 2023-02-22 23:25:31 -05:00
default_fmha_grouped.h fMHA: Sync FW with xFormers (#828) 2023-02-22 23:25:31 -05:00
fmha_backward_test.py fMHA: Add backward pass (#844) 2023-04-06 20:44:58 -04:00
fmha_grouped_problem_visitor.h New updates for 2.11 (#775) 2023-01-20 16:32:57 -05:00
fmha_grouped.h fMHA: Sync FW with xFormers (#828) 2023-02-22 23:25:31 -05:00
fused_multi_head_attention_backward.cu fMHA: Add backward pass (#844) 2023-04-06 20:44:58 -04:00
fused_multihead_attention_fixed_seqlen.cu Fix typos 2 (#842) 2023-03-09 23:22:56 -05:00
fused_multihead_attention_variable_seqlen.cu Fix typos 2 (#842) 2023-03-09 23:22:56 -05:00
gemm_kernel_utils.h fMHA: Add backward pass (#844) 2023-04-06 20:44:58 -04:00
kernel_backward.h fMHA: Add backward pass (#844) 2023-04-06 20:44:58 -04:00
kernel_forward.h fMHA: Add backward pass (#844) 2023-04-06 20:44:58 -04:00
piped_subprocess.py fMHA: Add backward pass (#844) 2023-04-06 20:44:58 -04:00