[Executorch][llama] Change runner to decouple prompt length from sequence length#9594
Merged
facebook-github-bot merged 2 commits intogh/kimishpatel/162/basefrom Mar 26, 2025
Merged
Conversation
…ence length Following previous diff now we can utilize entire kv cache to generate more tokens than max prompt length allowed. Differential Revision: [D69073908](https://our.internmc.facebook.com/intern/diff/D69073908/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/9594
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit f4f089e with merge base 644b7dd ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
kimishpatel
added a commit
that referenced
this pull request
Mar 25, 2025
…ence length Following previous diff now we can utilize entire kv cache to generate more tokens than max prompt length allowed. Differential Revision: [D69073908](https://our.internmc.facebook.com/intern/diff/D69073908/) ghstack-source-id: 273982703 Pull Request resolved: #9594
facebook-github-bot
added
the
CLA Signed
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D69073908 |
kimishpatel
added
the
release notes: examples
jackzhxng
approved these changes
Mar 25, 2025
…h from sequence length" length Following previous diff now we can utilize entire kv cache to generate more tokens than max prompt length allowed. Differential Revision: [D69073908](https://our.internmc.facebook.com/intern/diff/D69073908/) [ghstack-poisoned]
kimishpatel
added a commit
that referenced
this pull request
Mar 25, 2025
…ence length Pull Request resolved: #9594 Following previous diff now we can utilize entire kv cache to generate more tokens than max prompt length allowed. Differential Revision: [D69073908](https://our.internmc.facebook.com/intern/diff/D69073908/) ghstack-source-id: 274018812
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D69073908 |
facebook-github-bot
merged commit dcfa538
into
gh/kimishpatel/162/base
81 of 83 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
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
3 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.
Stack from ghstack (oldest at bottom):
length
Following previous diff now we can utilize entire kv cache to generate more
tokens than max prompt length allowed.
Differential Revision: D69073908