[ET-VK] Enable int8 tiled compute shader to be used with buffer tensors #10302
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
## 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 Differential Revision: [D73276277](https://our.internmc.facebook.com/intern/diff/D73276277/) [ghstack-poisoned]
SS-JIA
added a commit
that referenced
this pull request
Apr 18, 2025
## 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 Differential Revision: [D73276277](https://our.internmc.facebook.com/intern/diff/D73276277/) ghstack-source-id: 279008193 Pull Request resolved: #10302
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10302
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 4 New Failures, 6 Unrelated FailuresAs of commit 191e6c4 with merge base 5b7f235 ( NEW FAILURES - The following jobs have failed:
FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D73276277 |
This PR needs a
|
…uffer tensors" ## 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 Differential Revision: [D73276277](https://our.internmc.facebook.com/intern/diff/D73276277/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D73276277 |
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):
Context
As title. Allow the optimized int8 tiled compute shader to be usable for buffer-backed tensors as well.
Changes
Differential Revision: D73276277