Add tensor parallelism support for int4_weight_only quantization #1120
Conversation
This file contains 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
Summary: Following pytorch#988 we added TP support for int4_weight_only quantization in torchao that's using TensorCoreTiledLayout Addresses one work item in pytorch#988 Also clarified docs based on pytorch#386 Also restructructured the tests in test/dtypes/test_affine_quantized_tensor_parallel.py to not depend on torchao/utils.py to reduce the jumps people have to do to understand what is tested Test Plan: python test/dtypes/test_affine_quantized_tensor_parallel.py Reviewers: Subscribers: Tasks: Tags:
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/1120
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit ca241ed with merge base 3475aed ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
jainapurva
approved these changes
Oct 19, 2024
This was referenced Oct 19, 2024
yanbing-j
pushed a commit
to yanbing-j/ao
that referenced
this pull request
Dec 9, 2024
…and present it in a nicely formatted manner (pytorch#1120) * add stage metrics - total params per stage, total size * PR feedback * PR feedback, typing
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Outdated suggestions cannot be applied.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:
Following #939 we added TP support for int4_weight_only quantization in torchao that's using TensorCoreTiledLayout
Addresses one work item in #988
Also clarified docs based on #386
Also restructructured the tests in test/dtypes/test_affine_quantized_tensor_parallel.py to not depend on torchao/utils.py to reduce the jumps people have to do to understand what is tested
Test Plan:
python test/dtypes/test_affine_quantized_tensor_parallel.py
Reviewers:
Subscribers:
Tasks:
Tags: