[Executorch][llm] Add ring buffer based kv cache and mask calculation to MHA #10609
Conversation
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
… 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]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10609
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 0514d1e with merge base bf50527 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
This was referenced May 1, 2025
|
This pull request was exported from Phabricator. Differential Revision: D73891425 |
…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]
|
This pull request was exported from Phabricator. Differential Revision: D73891425 |
kimishpatel
added
the
release notes: examples
digantdesai
approved these changes
May 5, 2025
…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]
|
This pull request was exported from Phabricator. Differential Revision: D73891425 |
…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]
|
This pull request was exported from Phabricator. Differential Revision: D73891425 |
…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]
|
This pull request was exported from Phabricator. Differential Revision: D73891425 |
…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]
|
This pull request was exported from Phabricator. Differential Revision: D73891425 |
…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]
|
This pull request was exported from Phabricator. Differential Revision: D73891425 |
facebook-github-bot
merged commit b6c9bcd
into
gh/kimishpatel/186/base
91 of 94 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
kimishpatel
added a commit
that referenced
this pull request
May 13, 2025
… to MHA Pull Request resolved: #10609 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. ghstack-source-id: 283404675 @exported-using-ghexport Differential Revision: [D73891425](https://our.internmc.facebook.com/intern/diff/D73891425/)
kimishpatel
added a commit
that referenced
this pull request
May 13, 2025
… to MHA (#10833) This PR was created by the merge bot to help merge the original PR into the main branch. ghstack PR number: #10609 by @kimishpatel ^ Please use this as the source of truth for the PR details, comments, and reviews ghstack PR base: https://github.com/pytorch/executorch/tree/gh/kimishpatel/186/base ghstack PR head: https://github.com/pytorch/executorch/tree/gh/kimishpatel/186/head Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/kimishpatel/185/orig Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/kimishpatel/186/orig @diff-train-skip-merge Co-authored-by: Kimish Patel <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Stack from ghstack (oldest at bottom):
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