[ET-VK] Fast path for choose_qparams #14019
Merged
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
The current implementations of `choose_qparams` are too slow to be practically usable. As a temporary workaround to unblock LLM optimizations, this diff/PR introduces a fast path for computing per-channel quantization parameters for 2D matrices in the form of the choose_qparams_per_row shader. Differential Revision: [D81800024](https://our.internmc.facebook.com/intern/diff/D81800024/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14019
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit 2ee5b97 with merge base 1a7441f ( 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
This was referenced Sep 5, 2025
This PR needs a
|
|
This pull request was exported from Phabricator. Differential Revision: D81800024 |
manuelcandales
approved these changes
Sep 5, 2025
The current implementations of `choose_qparams` are too slow to be practically usable. As a temporary workaround to unblock LLM optimizations, this diff/PR introduces a fast path for computing per-channel quantization parameters for 2D matrices in the form of the choose_qparams_per_row shader. Differential Revision: [D81800024](https://our.internmc.facebook.com/intern/diff/D81800024/) [ghstack-poisoned]
The current implementations of `choose_qparams` are too slow to be practically usable. As a temporary workaround to unblock LLM optimizations, this diff/PR introduces a fast path for computing per-channel quantization parameters for 2D matrices in the form of the choose_qparams_per_row shader. Differential Revision: [D81800024](https://our.internmc.facebook.com/intern/diff/D81800024/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D81800024 |
facebook-github-bot
merged commit 6ec3deb
into
gh/SS-JIA/320/base
115 of 118 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
SS-JIA
pushed a commit
that referenced
this pull request
Sep 8, 2025
Pull Request resolved: #14019 The current implementations of `choose_qparams` are too slow to be practically usable. As a temporary workaround to unblock LLM optimizations, this diff/PR introduces a fast path for computing per-channel quantization parameters for 2D matrices in the form of the choose_qparams_per_row shader. ghstack-source-id: 308092877 @exported-using-ghexport Differential Revision: [D81800024](https://our.internmc.facebook.com/intern/diff/D81800024/)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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):
The current implementations of
choose_qparamsare too slow to be practically usable.As a temporary workaround to unblock LLM optimizations, this diff/PR introduces a fast path for computing per-channel quantization parameters for 2D matrices in the form of the choose_qparams_per_row shader.
Differential Revision: D81800024