Skip to content

[Executorch][llm] Add ring buffer based kv cache and mask calculation to MHA #10609

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

Merged
merged 7 commits into from
May 13, 2025
Merged

[Executorch][llm] Add ring buffer based kv cache and mask calculation to MHA #10609

Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
286c258
[Executorch][llm] Add ring buffer based kv cache and mask calculation…
kimishpatel May 1, 2025
3e5659b
Update on "[Executorch][llm] Add ring buffer based kv cache and mask …
kimishpatel May 5, 2025
7d3fdd7
Update on "[Executorch][llm] Add ring buffer based kv cache and mask …
kimishpatel May 7, 2025
646c2f9
Update on "[Executorch][llm] Add ring buffer based kv cache and mask …
kimishpatel May 9, 2025
38b2261
Update on "[Executorch][llm] Add ring buffer based kv cache and mask …
kimishpatel May 9, 2025
7ac15b0
Update on "[Executorch][llm] Add ring buffer based kv cache and mask …
kimishpatel May 10, 2025
0514d1e
Update on "[Executorch][llm] Add ring buffer based kv cache and mask …
kimishpatel May 12, 2025
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
Prev Previous commit
Next Next commit
Update on "[Executorch][llm] Add ring buffer based kv cache and mask … 
…calculation to MHA"

Leveraging previous work now we allow MHA to have ring buffer cache. If ring buffer cache is used
then we query the mask from kv cache and use that for sdpa instead of using precalculated mask.

In this process we had to adjsut ring buffer implementation to allow keeping the context of
full sliding window. See code for comment.

Differential Revision: [D73891425](https://our.internmc.facebook.com/intern/diff/D73891425/)

[ghstack-poisoned]
  • Loading branch information
@kimishpatel
kimishpatel committed May 9, 2025
commit 38b2261bf91ee1b819d1d3f0a13059401804dbd7

This merge commit was added into this branch cleanly.

There are no new changes to show, but you can still view the diff.