Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Re-organize SLL ops, pt 2 #3643

Closed
wants to merge 1 commit into from
Closed

Re-organize SLL ops, pt 2 #3643

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 0 additions & 5 deletions fbgemm_gpu/fbgemm_gpu/sll/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,6 @@
jagged_dense_bmm,
jagged_dense_elementwise_add,
jagged_dense_elementwise_mul_jagged_out,
jagged_dense_flash_attention,
jagged_flash_attention_basic,
jagged_jagged_bmm,
jagged_jagged_bmm_jagged_out,
Expand Down Expand Up @@ -321,10 +320,6 @@
"CUDA": jagged_dense_elementwise_add,
"AutogradCUDA": jagged_dense_elementwise_add,
},
"sll_jagged_dense_flash_attention": {
"CUDA": jagged_dense_flash_attention,
"AutogradCUDA": jagged_dense_flash_attention,
},
}

for op_name, dispatches in sll_cpu_registrations.items():
Expand Down
12 changes: 11 additions & 1 deletion fbgemm_gpu/fbgemm_gpu/sll/triton/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,12 +8,22 @@
# pyre-strict


from fbgemm_gpu.sll.triton.jagged_dense_flash_attention import ( # noqa F401
jagged_dense_flash_attention,
JaggedDenseFlashAttention, # noqa F401
)

from fbgemm_gpu.sll.triton.multi_head_jagged_flash_attention import ( # noqa F401
multi_head_jagged_flash_attention,
MultiHeadJaggedFlashAttention,
MultiHeadJaggedFlashAttention, # noqa F401
)

# pyre-ignore[5]
op_registrations = {
"sll_jagged_dense_flash_attention": {
"CUDA": jagged_dense_flash_attention,
"AutogradCUDA": jagged_dense_flash_attention,
},
"sll_multi_head_jagged_flash_attention": {
"CUDA": multi_head_jagged_flash_attention,
"AutogradCUDA": multi_head_jagged_flash_attention,
Expand Down
Loading
Loading