create staticmethod for quantizing weights of QATLinear and QATEmbedding #2079
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2079
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: ❌ 1 New Failure, 6 Unrelated FailuresAs of commit 7956303 with merge base 0045d88 ( BROKEN TRUNK - The following jobs failed but were 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. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D73201409 |
navsud
added
the
topic: not user facing
jerryzh168
approved these changes
Apr 19, 2025
…ing (pytorch#2079) Summary: For saving the quantized weights, we have been using adhoc notebooks with copy-pasted code from the convert method. This had been a source of numerical discrepancies. To avoid this issue, this diff adds separates the weight quantization logic in to a separate staticmethods so that we can reuse it. Reviewed By: jerryzh168 Differential Revision: D73201409
navsud
force-pushed
the
export-D73201409
branch
from
d953902 to
7956303
Compare
|
This pull request was exported from Phabricator. Differential Revision: D73201409 |
lisjin
pushed a commit
to lisjin/ao
that referenced
this pull request
Apr 22, 2025
Differential Revision: D73201409 Pull Request resolved: pytorch#2079
|
This pull request has been reverted by 896f61b. |
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.
Summary:
For saving the quantized weights, we have been using adhoc notebooks with copy-pasted code from the convert method.
This had been a source of numerical discrepancies. To avoid this issue, this diff adds separates the weight quantization logic in to a separate staticmethods so that we can reuse it.
Reviewed By: jerryzh168
Differential Revision: D73201409