Skip to content

Fix parameter name for values tensor in run_scaled_dot_product_attention #35

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix parameter name for values tensor in run_scaled_dot_product_attention #35

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
4 changes: 2 additions & 2 deletions tests/adapters.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,7 +89,7 @@ def run_swiglu(
def run_scaled_dot_product_attention(
Q: Float[Tensor, " ... queries d_k"],
K: Float[Tensor, " ... keys d_k"],
V: Float[Tensor, " ... values d_v"],
V: Float[Tensor, " ... keys d_v"],
mask: Bool[Tensor, " ... queries keys"] | None = None,
Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Also, shouldn't mask be of size "queries keys" instead of "... queries keys"?

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The masks can differ for each batch element, so ... is correct.

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ah, I considered that but thought not really necessary (thought either all batch samples attend to everything or all batch samples only attend to past tokens). Anyway, thanks for confirming! :)

) -> Float[Tensor, " ... queries d_v"]:
"""
Expand All @@ -99,7 +99,7 @@ def run_scaled_dot_product_attention(
Args:
Q (Float[Tensor, " ... queries d_k"]): Query tensor
K (Float[Tensor, " ... keys d_k"]): Key tensor
V (Float[Tensor, " ... values d_v"]): Values tensor
V (Float[Tensor, " ... keys d_v"]): Values tensor
mask (Bool[Tensor, " ... queries keys"] | None): Mask tensor
Returns:
Float[Tensor, " ... queries d_v"]: Output of SDPA
Expand Down