[ExecuTorch] Allow using custom SDPA for non-float32 dtypes in llama demo #5548
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
…demo Converting the input to and from float32 is faster than not using the op. h/t to torchchat, which does this already (though it had a bug, which I sent a patch for). Differential Revision: [D63158951](https://our.internmc.facebook.com/intern/diff/D63158951/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/5548
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit db8a68c with merge base b2517d6 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
swolchok
added a commit
that referenced
this pull request
Sep 23, 2024
…demo Converting the input to and from float32 is faster than not using the op. h/t to torchchat, which does this already (though it had a bug, which I sent a patch for). Differential Revision: [D63158951](https://our.internmc.facebook.com/intern/diff/D63158951/) ghstack-source-id: 244181863 Pull Request resolved: #5548
|
This pull request was exported from Phabricator. Differential Revision: D63158951 |
kimishpatel
approved these changes
Sep 23, 2024
|
This pull request has been merged in cab6335. |
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Outdated suggestions cannot be applied.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):
Converting the input to and from float32 is faster than not using the op. h/t to torchchat, which does this already (though it had a bug, which I sent a patch for).
Differential Revision: D63158951