kongo_junandClaude Fable 5
4f33190fe7
Run DiT models larger than VRAM (Wan 2.2 / Bernini-R 14B fp16, 28.6 GB on a 24 GB GPU) by keeping the first N transformer blocks in pinned system RAM and streaming each block to the GPU just-in-time during forward. - ModelPatcher ON_LOAD hook: swap blocks get LoRA patches baked in once, resident part is made fully GPU-resident (no per-layer LowVramPatch cast) - Synchronized H2D transfers (async pinned copies busy-loop hang on WDDM) - ON_DETACH restore; safe across model switching and LoRA changes - Requires --disable-dynamic-vram; Wan-family (.blocks) tested Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
4 lines
136 B
Python
4 lines
136 B
Python
from .blockswap import NODE_CLASS_MAPPINGS, NODE_DISPLAY_NAME_MAPPINGS
|
|
|
|
__all__ = ["NODE_CLASS_MAPPINGS", "NODE_DISPLAY_NAME_MAPPINGS"]
|