[Executorch] Use temp allocator for allocating scratch memory #16121
+729
−32
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: #15610 For small models dequantizing portions of v cache causes extra alloc overhead. Probably a better way to handle this is to dequantize entire v cache outside the model There isnt significant perf advantage from this yet but subsequent diffs will use caching allocator where this refactor help. ghstack-source-id: 327191612 @exported-using-ghexport Differential Revision: [D85532077](https://our.internmc.facebook.com/intern/diff/D85532077/)
Pull Request resolved: #15611 Meant to use this for temp allocator for kernels. Specifically for sdpa, it seems that on iOS there is a significant overhead coming from allocations ghstack-source-id: 327518047 @exported-using-ghexport Differential Revision: [D85532079](https://our.internmc.facebook.com/intern/diff/D85532079/)
Pull Request resolved: #15728 This allows us to leverage temp memory allocator and if that allocator is caching allocator it reduces the allocaiton overhead. ghstack-source-id: 327518050 @exported-using-ghexport Differential Revision: [D85532076](https://our.internmc.facebook.com/intern/diff/D85532076/)
pytorchbot
requested review from
jackzhxng,
larryliu0820 and
mergennachin
as code owners
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16121
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 4eda1bf with merge base 8af8252 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
kimishpatel
force-pushed
the
gh/kimishpatel/203/orig
branch
from
9574817 to
8b88a23
Compare
kimishpatel
requested review from
JacobSzwejbka and
kirklandsign
as code owners
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.
This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #15728 by @kimishpatel
^ 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/kimishpatel/211/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/kimishpatel/211/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/kimishpatel/203/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/kimishpatel/211/orig
Differential Revision: D85532076
@diff-train-skip-merge