[ET-VK] Enable int8 tiled compute shader to be used with buffer tensors #10415
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: #10302 ## Context As title. Allow the optimized int8 tiled compute shader to be usable for buffer-backed tensors as well. ## Changes * Generate buffer variants for the int8 linear tiled shader * Force the scales tensor to always be a buffer to reduce the number of shader variants that need to be generated. * Generate an additional variant that computes only 1 output row * Do not require output rows to be an exact multiple of 4 or 6 to use the tiled implementation ghstack-source-id: 279878372 Differential Revision: [D73276277](https://our.internmc.facebook.com/intern/diff/D73276277/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10415
Note: Links to docs will display an error until the docs builds have been completed. This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
This PR needs a
|
SS-JIA
approved these changes
Apr 23, 2025
SS-JIA
added a commit
that referenced
this pull request
Apr 23, 2025
* main: [ET-VK] Enable int8 tiled compute shader to be used with buffer tensors (#10415) Revert "Migrate elementwise_util callers to the variants with out_dtypes in template arguments" (#10411) Revert "Save some size in dtype_util when dtype selective build is not in use" (#10410) Generalize view_copy fusion. Add job_arn to benchmark result (#10372) Revert "Minibench refactor (#10376)" (#10405) Revert "Arm backend: Populate __init__.py for quantizer and Arm root" (#10395) Arm backend: Convert assert to throw ValueError in op_log (#10392) Arm backend: Add Tutorial to Example tab on the Docs page (#10386) Arm backend: Update node visitors to support TOSA 1.0 (#10390) Arm backend: Make it easier to generate non delegated/quantized PTEs (#10387) Arm backend: Allow --quantize in non delegated using aot_arm_compiler (#10385) Arm backend: Set REGIONCFG registers of the Ethos-U (#10388)
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: #10302 by @SS-JIA
^ 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/SS-JIA/214/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/214/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/main
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/214/orig
@diff-train-skip-merge