Merged
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/3053
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 6bb3ebd with merge base 8e2ca35 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
5 tasks
jerryzh168
reviewed
Sep 24, 2025
jerryzh168
reviewed
Sep 24, 2025
| def _(func, types, args, kwargs): | ||
| old_float8_tensor, dim, index = args | ||
| assert dim == 0, f"Float8Tensor aten.select.int with {dim=} is not yet supported" | ||
| new_float8_tensor = old_float8_tensor.__class__( |
Contributor
There was a problem hiding this comment.
nit: is it better to use Float8Tensor directly here? or old_float8_tensor.__class__? we have been using Float8Tensor in other functions so far
Contributor
Author
There was a problem hiding this comment.
I used the syntax in the function right above which uses __class__, so I guess there is already a mix? If we want consistency, maybe we can do a codemod in a future PR.
jerryzh168
approved these changes
Sep 24, 2025
Summary: This is useful for stitching together 2D weights to a 3D weight, specifically this happens in vLLM for HF models where expert weights are 2D. Test Plan: ```bash pytest test/quantization/quantize_/workflows/float8/test_float8_tensor.py -x -s -k index ``` Reviewers: Subscribers: Tasks: Tags:
95f42d0 to
6bb3ebd
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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:
This is useful for stitching together 2D weights to a 3D weight, specifically this happens in vLLM for HF models where expert weights are 2D.
Test Plan:
Reviewers:
Subscribers:
Tasks:
Tags: