[ET-VK][ez] Use standard quant naming scheme for quantized ops #10587
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 Use standard naming scheme for quantized operators introduced in the previous PR. For weight only quantized linear operators, the names introduced are: `linear_qcsnw`: * q - quantized * c - per-channel / channelswise * s - symmetric * n - number of bits (qcs4w for 4-bit quant, qcs8w for 8-bit quant) * w - weight quantized `linear_qga4w`: * q - quantized * g - per-group / groupwise * a - affine * 4 - quantized to 4 bits * w - weight quantized ## Changes Rename instances of `q_8w_linear` to `linear_qcs8w` or `linear_qcsnw`. Rename instances of `q_4w_linear` to `linear_qga4w`. Rename cpp files to match the new naming convention. Differential Revision: [D73941992](https://our.internmc.facebook.com/intern/diff/D73941992/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10587
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 1 PendingAs of commit f23c350 with merge base 280db15 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
This was referenced Apr 30, 2025
|
This pull request was exported from Phabricator. Differential Revision: D73941992 |
trivedivivek
approved these changes
May 1, 2025
… ops" ## Context Use standard naming scheme for quantized operators introduced in the previous PR. For weight only quantized linear operators, the names introduced are: `linear_qcsnw`: * q - quantized * c - per-channel / channelswise * s - symmetric * n - number of bits (qcs4w for 4-bit quant, qcs8w for 8-bit quant) * w - weight quantized `linear_qga4w`: * q - quantized * g - per-group / groupwise * a - affine * 4 - quantized to 4 bits * w - weight quantized ## Changes Rename instances of `q_8w_linear` to `linear_qcs8w` or `linear_qcsnw`. Rename instances of `q_4w_linear` to `linear_qga4w`. Rename cpp files to match the new naming convention. Differential Revision: [D73941992](https://our.internmc.facebook.com/intern/diff/D73941992/) [ghstack-poisoned]
|
This pull request was exported from Phabricator. Differential Revision: D73941992 |
facebook-github-bot
merged commit 28bc8e0
into
gh/SS-JIA/221/base
84 of 88 checks passed
facebook-github-bot
temporarily deployed
to
cherry-pick-bot
GitHub Actions
Inactive
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
Use standard naming scheme for quantized operators introduced in the previous PR.
For weight only quantized linear operators, the names introduced are:
linear_qcsnw:linear_qga4w:Changes
Rename instances of
q_8w_lineartolinear_qcs8worlinear_qcsnw.Rename instances of
q_4w_lineartolinear_qga4w.Rename cpp files to match the new naming convention.
Differential Revision: D73941992