[Quantization] Fused Triton kernel for NVFP4 FP8 scale sweep search #1387
Codecov / codecov/project
succeeded
May 8, 2026 in 0s
76.82% (-0.58%) compared to e2d29c8
View this Pull Request on Codecov
76.82% (-0.58%) compared to e2d29c8
Details
Codecov Report
❌ Patch coverage is 72.22222% with 25 lines in your changes missing coverage. Please review.
✅ Project coverage is 76.82%. Comparing base (e2d29c8) to head (c42de7f).
| Files with missing lines | Patch % | Lines |
|---|---|---|
| ...torch/kernels/quantization/gemm/nvfp4_fp8_sweep.py | 50.00% | 23 Missing |
| modelopt/torch/quantization/calib/mse.py | 94.59% | 2 Missing |
Additional details and impacted files
@@ Coverage Diff @@
## main #1387 +/- ##
==========================================
- Coverage 77.40% 76.82% -0.58%
==========================================
Files 476 478 +2
Lines 51319 51404 +85
==========================================
- Hits 39721 39492 -229
- Misses 11598 11912 +314 ☔ 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.
Loading