biondizzle 00b766af60 feat: add progress bars for expert quantization and post-load conversion ...

Visual feedback during the slow parts of model loading:
  NVFP4 experts [████████████████░░░░]  80% (26/32)
  NVFP4 convert [██████░░░░░░░░░░░░░░]  30% (20/61)

Updates every 10% so it's not spammy.

2026-05-16 04:14:07 +00:00

..

patches

feat: add progress bars for expert quantization and post-load conversion

2026-05-16 04:14:07 +00:00

nvfp4_cutedsl.py

fix: L1 gate/up split — intermediate_size is per-projection, not fused

2026-05-16 04:04:40 +00:00