-
Notifications
You must be signed in to change notification settings - Fork 536
[MPS] Add index.Tensor and aten.logical_not #3221
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[MPS] Add index.Tensor and aten.logical_not #3221
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/3221
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 1 Unrelated FailureAs of commit 2b833bd with merge base 1eaed2b ( NEW FAILURE - The following job has failed:
FLAKY - The following job failed but was likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Thank you! The logical op is actually from decomposing sdpa - if the sdpa is not ready yet, maybe can use the simpler version #3165 which has fewer ops than the decomposing |
@cccclai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
d13bb4e
to
1c9fda5
Compare
|
oh sorry pointed to a wrong pr...should be this one #3037. Regarding the test failure, probably @shoumikhin knows more. Will ping him tomorrow |
@cccclai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
1c9fda5
to
2b833bd
Compare
@cccclai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
@pytorchbot cherry-pick --onto release/0.2 -c regression |
Summary: Add missing llama ops for MPS delegate: - `index.Tensor` - `logical_not` `index.put` works correctly for generating 1 token, but gives incorrect results on 2nd token. This remains disabled. Summary of changes: - Adds missing llama2 ops - Adds support for launching Metal kernels instead of MPSGraph ops (if MPSGraph doesn't have the support) cc cccclai , shoumikhin Pull Request resolved: #3221 Reviewed By: shoumikhin Differential Revision: D56447710 Pulled By: cccclai fbshipit-source-id: 778a485df5e67d1afd006b42f07b69c8a3961223 (cherry picked from commit 02a6b66)
Cherry picking #3221The cherry pick PR is at #3267 and it is recommended to link a regression cherry pick PR with an issue Details for Dev Infra teamRaised by workflow job |
Summary: Add missing llama ops for MPS delegate: - `index.Tensor` - `logical_not` `index.put` works correctly for generating 1 token, but gives incorrect results on 2nd token. This remains disabled. Summary of changes: - Adds missing llama2 ops - Adds support for launching Metal kernels instead of MPSGraph ops (if MPSGraph doesn't have the support) cc cccclai , shoumikhin Pull Request resolved: #3221 Reviewed By: shoumikhin Differential Revision: D56447710 Pulled By: cccclai fbshipit-source-id: 778a485df5e67d1afd006b42f07b69c8a3961223 (cherry picked from commit 02a6b66) Co-authored-by: Denis Vieriu <[email protected]>
Add missing llama ops for MPS delegate:
index.Tensor
logical_not
index.put
works correctly for generating 1 token, but gives incorrect results on 2nd token. This remains disabled.Summary of changes:
cc @cccclai , @shoumikhin