Skip to content

Working branch for NVFP4 MSE #1403

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
cjluo-nv wants to merge 8 commits into
base: main
Choose a base branch
from

[Quantization] MSE-calibrate every per-expert weight in fused-experts…

ca23dcd
Select commit
Loading
Failed to load commit list.
Draft

Working branch for NVFP4 MSE #1403

[Quantization] MSE-calibrate every per-expert weight in fused-experts…
ca23dcd
Select commit
Loading
Failed to load commit list.
Codecov / codecov/project failed May 7, 2026 in 0s

74.63% (-2.28%) compared to acfab41

View this Pull Request on Codecov

74.63% (-2.28%) compared to acfab41

Details

Codecov Report

❌ Patch coverage is 58.72340% with 97 lines in your changes missing coverage. Please review.
✅ Project coverage is 74.63%. Comparing base (acfab41) to head (ca23dcd).
⚠️ Report is 22 commits behind head on main.

Files with missing lines Patch % Lines
modelopt/torch/quantization/model_calib.py 63.33% 44 Missing ⚠️
...torch/kernels/quantization/gemm/nvfp4_fp8_sweep.py 56.60% 23 Missing ⚠️
modelopt/torch/export/unified_export_hf.py 5.88% 16 Missing ⚠️
modelopt/torch/quantization/plugins/huggingface.py 12.50% 7 Missing ⚠️
modelopt/torch/export/moe_utils.py 0.00% 6 Missing ⚠️
...odelopt/torch/quantization/qtensor/nvfp4_tensor.py 0.00% 1 Missing ⚠️
Additional details and impacted files 
@@            Coverage Diff             @@
##             main    #1403      +/-   ##
==========================================
- Coverage   76.90%   74.63%   -2.28%     
==========================================
  Files         471      478       +7     
  Lines       50562    53235    +2673     
==========================================
+ Hits        38886    39730     +844     
- Misses      11676    13505    +1829

☔ 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.
View more details on Codecov