[Executorch][llm] Enable leveraging ring kv cache via module swap #10835
+2,081
−140
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
Pull Request resolved: #10608 Introduced CachePositionManager to keep track of what is the position for each slot in ring kv cache. This is used to generate mask. ghstack-source-id: 283404678 @exported-using-ghexport Differential Revision: [D73891427](https://our.internmc.facebook.com/intern/diff/D73891427/)
… 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/)
Pull Request resolved: #10610 This allows us to use ring buffer kv cache ghstack-source-id: 283404676 @exported-using-ghexport Differential Revision: [D73891424](https://our.internmc.facebook.com/intern/diff/D73891424/)
Pull Request resolved: #10611 This allows us to make some of the attention modules to use sliding window kv cache. Will help enable models like gemma3. ghstack-source-id: 283404677 Differential Revision: [D73891426](https://our.internmc.facebook.com/intern/diff/D73891426/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10835
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit ed32169 with merge base bf50527 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
kimishpatel
force-pushed
the
gh/kimishpatel/187/orig
branch
from
bfcaf89 to
b994a1a
Compare
kimishpatel
requested review from
iseeyuan,
larryliu0820 and
swolchok
as code owners
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.
This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #10611 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/188/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/kimishpatel/188/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/kimishpatel/187/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/kimishpatel/188/orig
@diff-train-skip-merge