Aaron Meese 67d9ef79d9 feat: add --gpu-memory-utilization CLI flag ...

Add a --gpu-memory-utilization flag (0.0-1.0, default 0.85) that controls
the fraction of GPU VRAM available for model loading. Plumbed from CLI
through AbliterationPipeline to load_model's max_memory calculation.

Useful on dedicated GPU setups where the default 15% reserve is wasteful
and causes unnecessary CPU offloading on models that would otherwise fit.

2026-08-15 02:47:28 -04:00

..

__init__.py

Add files via upload

2026-03-04 12:38:18 -08:00

loader.py

feat: add --gpu-memory-utilization CLI flag

2026-08-15 02:47:28 -04:00