Commit Graph

4 Commits

Author SHA1 Message Date
3907838409 Remove ModuleList patch (already fixed in modelopt 0.45), fix numbering 2026-05-09 06:10:18 +00:00
382c1d872f Fix quant_module import path 2026-05-09 06:09:17 +00:00
9291165ba0 Fix imports: QUANT_CFG_CHOICES is in hf_ptq, not modelopt config 2026-05-09 06:08:35 +00:00
a0bacb3cf6 Replace shell wrapper with in-process quantize script
- New scripts/quantize_nvfp4.py: runs full ModelOpt pipeline in-process
- Saves calibrated state after calibration (insurance against export crashes)
- Patches modelopt for V4: ModuleList quantizers, stale GPU tensor safety
- --export-only flag to retry export from saved calibration state
- Removed old model_opt_nvfp4_full.py (shell wrapper)
- Updated README with new pipeline docs and bug #5/#6
2026-05-09 06:07:22 +00:00