Update torchao usage for XPU and CPU#45560
Merged
stevhliu merged 1 commit intohuggingface:mainfrom Apr 22, 2026
Merged
Conversation
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
Contributor
Author
|
Hi @stevhliu . Would you please review the PR? Thanks! |
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Update torchao quantization doc to align with latest torchao API changes.
Changes
Int4XPULayoutandZeroPointDomainsetup —Int4WeightOnlyConfignow handles these internally.Int4WeightOnlyOpaqueTensorConfigwithPrototypeInt4WeightOnlyConfig..to()fix: Split.to(device, dtype)into.to(device).to(dtype)to avoid incorrect casting.Why
torchao updated its APIs: XPU int4 config now auto-handles layout/zero-point internally, CPU int4 config was renamed and moved to a new module path. The
.to()chaining fix ensures device placement and dtype casting are applied correctly.