[TMTensor][LinalgExt] Fuse causal mask into attention decomposition#23999
Draft
keshavvinayak01 wants to merge 1 commit intoiree-org:mainfrom
Draft
[TMTensor][LinalgExt] Fuse causal mask into attention decomposition#23999keshavvinayak01 wants to merge 1 commit intoiree-org:mainfrom
keshavvinayak01 wants to merge 1 commit intoiree-org:mainfrom
Conversation
Add is_causal attribute to AttentionOp and OnlineAttentionOp. When set, the causal condition (k2 > m) is computed inline from loop indices during decomposition, fused into the max-reduction and exp steps. This eliminates the need for a materialized N×N mask tensor. Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Keshav Vinayak Jha <keshavvinayakjha@gmail.com>
keshavvinayak01
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add
is_causalattribute toAttentionOpandOnlineAttentionOp. When set, the causal condition(k2 > m)is computed inline from loop indices during decomposition, fused into the max-reduction and exp steps. This eliminates the need for a materialized N×N mask tensor.