Skip to content

Conversation

@sychen52
Copy link
Contributor

@sychen52 sychen52 commented Dec 11, 2025

What does this PR do? new feature

Overview: use kitchen FA in huggingface plugin

Usage

# Add a code snippet demonstrating how to use this

Testing

Before your PR is "Ready for review"

  • Make sure you read and follow Contributor guidelines and your commits are signed.
  • Is this change backward compatible?: Yes/No
  • Did you write any new necessary tests?: Yes/No
  • Did you add or update any necessary documentation?: Yes/No
  • Did you update Changelog?: Yes/No

Additional Information

@sychen52 sychen52 self-assigned this Dec 11, 2025
@copy-pr-bot
Copy link

copy-pr-bot bot commented Dec 11, 2025

Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually.

Contributors can view more details about this message here.

@codecov
Copy link

codecov bot commented Dec 11, 2025

Codecov Report

❌ Patch coverage is 66.66667% with 3 lines in your changes missing coverage. Please review.
✅ Project coverage is 74.65%. Comparing base (bdd10c2) to head (35aab2e).
⚠️ Report is 1 commits behind head on main.

Files with missing lines Patch % Lines
.../torch/quantization/nn/modules/tensor_quantizer.py 66.66% 3 Missing ⚠️
Additional details and impacted files
@@            Coverage Diff             @@
##             main     #674      +/-   ##
==========================================
- Coverage   74.65%   74.65%   -0.01%     
==========================================
  Files         192      192              
  Lines       18909    18918       +9     
==========================================
+ Hits        14117    14123       +6     
- Misses       4792     4795       +3     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

@sychen52 sychen52 marked this pull request as ready for review December 19, 2025 06:04
@sychen52 sychen52 requested a review from a team as a code owner December 19, 2025 06:04
@sychen52 sychen52 requested a review from kaix-nv December 19, 2025 06:04
Signed-off-by: Shiyang Chen <shiychen@nvidia.com>
Signed-off-by: Shiyang Chen <shiychen@nvidia.com>
Comment on lines +428 to +448
@property
def is_mxfp4(self):
"""Check if is MXFP4."""
return (
self.is_mx_format and self.num_bits == (2, 1) and self.block_sizes.get(-1, None) == 32
)

@property
def is_mxfp6(self):
"""Check if is MXFP6."""
return (
self.is_mx_format and self.num_bits == (3, 2) and self.block_sizes.get(-1, None) == 32
)

@property
def is_mxfp8(self):
"""Check if is MXFP8."""
return (
self.is_mx_format and self.num_bits == (4, 3) and self.block_sizes.get(-1, None) == 32
)

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can you add arguments to is_mx_format method instead of elaborating like this? We would need to make is_max_format a regular method instead of a property - but that should be okay

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants