Add from_int4_tensor in Int4PreshuffledTensor#2978
Merged
Conversation
Summary: Added a classmethod `from_int4_tensor` to convert a plain `Int4Tensor` to `Int4PreshuffledTensor` This is in preparation for supporting Int4PreshuffledTensor in vllm, which requires the tensor to be sliced before inference, see https://github.com/pytorch/ao/blob/186aeb01664687d14108ada420c475cc783e1643/torchao/testing/utils.py#L429 for details but Int4PreshuffledTensor can't be easiliy sliced while also preserving alias, so we plan to slice the Plain int4 tensor instead and then convert to Int4PreshuffledTensor at a later stage. Next PR is going to add a top level API in prototype to convert from int4 tensor to int4 preshuffled tensor Test Plan: python test/quantization/quantize_/workflows/int4/test_int4_preshuffled_tensor.py -k test_from_int4_tensor Reviewers: Subscribers: Tasks: Tags:
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2978
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 22e0acb with merge base 186aeb0 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
metascroy
approved these changes
Sep 11, 2025
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary:
Added a classmethod
from_int4_tensorto convert a plainInt4TensortoInt4PreshuffledTensorThis is in preparation for supporting Int4PreshuffledTensor in vllm, which requires the tensor to be sliced before inference, see
ao/torchao/testing/utils.py
Line 429 in 186aeb0
but Int4PreshuffledTensor can't be easiliy sliced while also preserving alias, so we plan to slice the Plain int4 tensor instead and then convert to Int4PreshuffledTensor at a later stage.
Next PR is going to add a top level API in prototype to convert from int4 tensor to int4 preshuffled tensor
Test Plan:
python test/quantization/quantize_/workflows/int4/test_int4_preshuffled_tensor.py -k test_from_int4_tensor
Reviewers:
Subscribers:
Tasks:
Tags: