implement position encoding for shifted tokens #7114
Merged
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: #6560 Right now, rope related code scatters around a few different places in `llama_transformer`. It makes it hard to make changes to rope related things. This PR moves all rope related logic into its own module. ghstack-source-id: 255543205 Differential Revision: [D65173598](https://our.internmc.facebook.com/intern/diff/D65173598/)
Pull Request resolved: #6646 In AttentionSink, it uses tokens' positions in the KVCache instead of the actual text. When tokens get shifted in KVCache, it needs to update q and k's position embedding. In the original [implementation](https://github.com/mit-han-lab/streaming-llm) of AttentionSink with Rope, it caches the original q and k in KVCache and apply position embedding during inference. This PR adds `RopeWithAttentionSink`. It assumes that q and k are already encoded with their original position. When we shift tokens, we reapply the position delta. This has two benefits: - minimize our code since our existing `llama_transformer` applies rope embedding before doing KVCache update - avoid performance regression when tokens are not shifted because we don't need to reapply position encoding in KVCache for them ghstack-source-id: 255579838 Differential Revision: [D65366440](https://our.internmc.facebook.com/intern/diff/D65366440/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7114
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 923e31e with merge base b8fbc48 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
kirklandsign
approved these changes
Nov 27, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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: #6646
^ 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/helunwencser/71/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/helunwencser/71/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/helunwencser/68/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/helunwencser/71/orig
@diff-train-skip-merge