Add support for Int4GroupwisePreshuffleTensor for fbgemm #2421
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/2421
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit e664a1e with merge base 5a50667 ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
jerryzh168
added a commit
that referenced
this pull request
Jun 22, 2025
jerryzh168
force-pushed
the
jerryzh168/stack/1
branch
from
565e596 to
65a1373
Compare
facebook-github-bot
added
the
CLA Signed
jerryzh168
added
the
topic: new feature
jerryzh168
force-pushed
the
jerryzh168/stack/1
branch
from
65a1373 to
8dcecf4
Compare
jerryzh168
changed the title
jerryzh168
force-pushed
the
jerryzh168/stack/1
branch
3 times, most recently
from
44b79dd to
6ce4c7b
Compare
jerryzh168
force-pushed
the
jerryzh168/stack/1
branch
from
6ce4c7b to
027648f
Compare
vkuzo
reviewed
Jun 25, 2025
vkuzo
reviewed
Jun 25, 2025
| if importlib.util.find_spec("fbgemm_gpu") is None: | ||
| quantize_int4_preshuffle = None | ||
| else: | ||
| from fbgemm_gpu.experimental.gen_ai.quantize import quantize_int4_preshuffle |
There was a problem hiding this comment.
is this a prototype API? If yes, should the torchao version also be prototype? what does "experimental" mean in the folder structure here?
There was a problem hiding this comment.
it is stable and production ready, and used in production. it's just bad naming according to @jwfromm, and they have a plan to get rid of it
vkuzo
reviewed
Jun 25, 2025
jerryzh168
force-pushed
the
jerryzh168/stack/1
branch
5 times, most recently
from
ccd2cba to
69a215e
Compare
Summary: Note: slice is not working yet, others are working Test Plan: python test/dtypes/test_int4_groupwise_preshuffle.py Reviewers: Subscribers: Tasks: Tags: stack-info: PR: #2421, branch: jerryzh168/stack/1
jerryzh168
force-pushed
the
jerryzh168/stack/1
branch
from
69a215e to
e664a1e
Compare
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.
Stacked PRs:
transpose_inputfrom fbgemm configs #2422Add support for Int4GroupwisePreshuffleTensor for fbgemm
Summary:
Note: slice is not working yet, others are working
Test Plan:
python test/dtypes/test_int4_groupwise_preshuffle.py
Reviewers:
Subscribers:
Tasks:
Tags: