Simplify core attention return types to Tensor#537
Open
stashuk-olek wants to merge 3 commits into
Open
Conversation
meta-cla
Bot
added
the
CLA Signed
|
@stashuk-olek has exported this pull request. If you are a Meta employee, you can view the originating Diff in D92927085. |
stashuk-olek
added a commit
to stashuk-olek/multimodal
that referenced
this pull request
Feb 12, 2026
Summary: After removing all consumers of `head_mask`, `return_attn_weights`, and `attn_probs` in the previous commits, the core attention module can be simplified. This commit: - Removes `head_mask` param from `scaled_dot_product_attention` and `SelfAttention.forward` - Changes return types from `Tuple[Tensor, Tensor]` to `Tensor` (no longer returning attention probabilities) - Removes `return_attn_weights` param and tuple unpacking logic from `MultiHeadAttention.forward` - Cleans up unused imports (`Tuple`, `Union`) No behavioral change — the attention computation itself is unchanged. Differential Revision: D92927085
stashuk-olek
force-pushed
the
export-D92927085
branch
from
814f4c6 to
6072fa3
Compare
stashuk-olek
added a commit
to stashuk-olek/multimodal
that referenced
this pull request
Feb 13, 2026
Summary: After removing all consumers of `head_mask`, `return_attn_weights`, and `attn_probs` in the previous commits, the core attention module can be simplified. This commit: - Removes `head_mask` param from `scaled_dot_product_attention` and `SelfAttention.forward` - Changes return types from `Tuple[Tensor, Tensor]` to `Tensor` (no longer returning attention probabilities) - Removes `return_attn_weights` param and tuple unpacking logic from `MultiHeadAttention.forward` - Cleans up unused imports (`Tuple`, `Union`) No behavioral change — the attention computation itself is unchanged. Reviewed By: OmarPavel Differential Revision: D92927085
stashuk-olek
added a commit
to stashuk-olek/multimodal
that referenced
this pull request
Feb 13, 2026
Summary: After removing all consumers of `head_mask`, `return_attn_weights`, and `attn_probs` in the previous commits, the core attention module can be simplified. This commit: - Removes `head_mask` param from `scaled_dot_product_attention` and `SelfAttention.forward` - Changes return types from `Tuple[Tensor, Tensor]` to `Tensor` (no longer returning attention probabilities) - Removes `return_attn_weights` param and tuple unpacking logic from `MultiHeadAttention.forward` - Cleans up unused imports (`Tuple`, `Union`) No behavioral change — the attention computation itself is unchanged. Reviewed By: OmarPavel Differential Revision: D92927085
stashuk-olek
force-pushed
the
export-D92927085
branch
from
6072fa3 to
5c1501b
Compare
stashuk-olek
added a commit
to stashuk-olek/multimodal
that referenced
this pull request
Feb 13, 2026
Summary: After removing all consumers of `head_mask`, `return_attn_weights`, and `attn_probs` in the previous commits, the core attention module can be simplified. This commit: - Removes `head_mask` param from `scaled_dot_product_attention` and `SelfAttention.forward` - Changes return types from `Tuple[Tensor, Tensor]` to `Tensor` (no longer returning attention probabilities) - Removes `return_attn_weights` param and tuple unpacking logic from `MultiHeadAttention.forward` - Cleans up unused imports (`Tuple`, `Union`) No behavioral change — the attention computation itself is unchanged. Reviewed By: OmarPavel Differential Revision: D92927085
stashuk-olek
force-pushed
the
export-D92927085
branch
from
5c1501b to
bb3e8d6
Compare
stashuk-olek
added a commit
to stashuk-olek/multimodal
that referenced
this pull request
Feb 13, 2026
Summary: After removing all consumers of `head_mask`, `return_attn_weights`, and `attn_probs` in the previous commits, the core attention module can be simplified. This commit: - Removes `head_mask` param from `scaled_dot_product_attention` and `SelfAttention.forward` - Changes return types from `Tuple[Tensor, Tensor]` to `Tensor` (no longer returning attention probabilities) - Removes `return_attn_weights` param and tuple unpacking logic from `MultiHeadAttention.forward` - Cleans up unused imports (`Tuple`, `Union`) No behavioral change — the attention computation itself is unchanged. Reviewed By: OmarPavel Differential Revision: D92927085
stashuk-olek
added a commit
to stashuk-olek/multimodal
that referenced
this pull request
Feb 13, 2026
Summary: After removing all consumers of `head_mask`, `return_attn_weights`, and `attn_probs` in the previous commits, the core attention module can be simplified. This commit: - Removes `head_mask` param from `scaled_dot_product_attention` and `SelfAttention.forward` - Changes return types from `Tuple[Tensor, Tensor]` to `Tensor` (no longer returning attention probabilities) - Removes `return_attn_weights` param and tuple unpacking logic from `MultiHeadAttention.forward` - Cleans up unused imports (`Tuple`, `Union`) No behavioral change — the attention computation itself is unchanged. Reviewed By: OmarPavel Differential Revision: D92927085
… weights in FLAVA (facebookresearch#535) Summary: The `attentions` field on `TransformerOutput` and `return_attn_weights`/`head_mask` parameters in the FLAVA encoder stack were never used by any consumer. This diffs cleans it up. Later the intent is to simplify attention usage / use common API for them. Reviewed By: OmarPavel Differential Revision: D92927086
…h#536) Summary: Remove dead `head_mask`, `return_attn_weights`, and `attention_weights` from the VideoGPT stack. These features were never used by any consumer — `head_mask` was always `None` or all-ones, and `return_attn_weights` was always `False` except in tests that verified the feature itself. Reviewed By: OmarPavel Differential Revision: D92927089
Summary: After removing all consumers of `head_mask`, `return_attn_weights`, and `attn_probs` in the previous commits, the core attention module can be simplified. This commit: - Removes `head_mask` param from `scaled_dot_product_attention` and `SelfAttention.forward` - Changes return types from `Tuple[Tensor, Tensor]` to `Tensor` (no longer returning attention probabilities) - Removes `return_attn_weights` param and tuple unpacking logic from `MultiHeadAttention.forward` - Cleans up unused imports (`Tuple`, `Union`) No behavioral change — the attention computation itself is unchanged. Reviewed By: OmarPavel Differential Revision: D92927085
stashuk-olek
force-pushed
the
export-D92927085
branch
from
bb3e8d6 to
b0c1de3
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary:
After removing all consumers of
head_mask,return_attn_weights, andattn_probsin the previous commits, the core attention module can be simplified. This commit:head_maskparam fromscaled_dot_product_attentionandSelfAttention.forwardTuple[Tensor, Tensor]toTensor(no longer returning attention probabilities)return_attn_weightsparam and tuple unpacking logic fromMultiHeadAttention.forwardTuple,Union)No behavioral change — the attention computation itself is unchanged.
Differential Revision: D92927085