[ET-VK] Optimizing buffer to int8 quantized packing op to improve width packed performance.#12388
[ET-VK] Optimizing buffer to int8 quantized packing op to improve width packed performance.#12388trviv wants to merge 2 commits into
Conversation
…th packed performance. This diff simplifies looping in int8 quantized packing operation for width pack tensor, to improve performance. Differential Revision: [D78143041](https://our.internmc.facebook.com/intern/diff/D78143041/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12388
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (5 Unrelated Failures)As of commit 2ac3962 with merge base 31ba959 ( FLAKY - The following job failed but was likely due to flakiness present on trunk:
BROKEN TRUNK - The following jobs failed but was present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
…th packed performance. This diff simplifies looping in int8 quantized packing operation for width pack tensor, to improve performance. Differential Revision: [D78143041](https://our.internmc.facebook.com/intern/diff/D78143041/) ghstack-source-id: 295570980 Pull Request resolved: #12388
|
This pull request was exported from Phabricator. Differential Revision: D78143041 |
…improve width packed performance." This diff simplifies looping in int8 quantized packing operation for width pack tensor, to improve performance. Differential Revision: [D78143041](https://our.internmc.facebook.com/intern/diff/D78143041/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D78143041 |
|
Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as |
|
Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as |
2 similar comments
|
Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as |
|
Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as |
Stack from ghstack (oldest at bottom):
This diff simplifies looping in int8 quantized packing operation for width pack tensor, to improve performance.
Differential Revision: D78143041