-
Notifications
You must be signed in to change notification settings - Fork 712
[Executorch][LLM] Use caching allocator for runner #15710
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
base: gh/kimishpatel/210/base
Are you sure you want to change the base?
Conversation
We observed that on iOS it improves perf by 6% because SDPA op does temp allocations. No significant difference on android though. Differential Revision: [D86120038](https://our.internmc.facebook.com/intern/diff/D86120038/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15710
Note: Links to docs will display an error until the docs builds have been completed. ❌ 127 New Failures, 1 Unrelated FailureAs of commit c826be1 with merge base aba44fd ( NEW FAILURES - The following jobs have 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. |
We observed that on iOS it improves perf by 6% because SDPA op does temp allocations. No significant difference on android though. Differential Revision: [D86120038](https://our.internmc.facebook.com/intern/diff/D86120038/) ghstack-source-id: 322129671 Pull Request resolved: #15710
This PR needs a
|
| model_path, data_files, Module::LoadMode::File); | ||
| model_path, | ||
| data_files, | ||
| Module::LoadMode::File, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
we dont use mmap? @larryliu0820
Stack from ghstack (oldest at bottom):
We observed that on iOS it improves perf by 6% because SDPA op does temp allocations.
No significant difference on android though.
Differential Revision: D86120038