Skip to content

Replace two-einsum OuterProductMean with fused three-way einsum #674

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

Closed
mooreneural wants to merge 1 commit into from
Closed

Replace two-einsum OuterProductMean with fused three-way einsum #674

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
8 changes: 5 additions & 3 deletions src/alphafold3/model/network/modules.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -403,9 +403,11 @@ def compute_chunk(left_act):
# so it will be treated as the real batch by XLA (both during the forward
# and the backward pass)
left_act = jnp.transpose(left_act, [0, 2, 1])
act = jnp.einsum('acb,ade->dceb', left_act, right_act)
act = jnp.einsum('dceb,cef->dbf', act, output_w) + output_b
return jnp.transpose(act, [1, 0, 2])
# Fused three-way einsum: XLA contracts the two C_outer dims before
# summing over MSA, avoiding the large [N, C, C, chunk] intermediate
# (~256 MB at N=1024, C=32, chunk=128, bfloat16; ~72 MB with this form).
act = jnp.einsum('acb,ade,cef->dbf', left_act, right_act, output_w)
return jnp.transpose(act, [1, 0, 2]) + output_b

act = mapping.inference_subbatch(
compute_chunk,
Expand Down