kijai 99c3978da4 Reduce peak VRAM usage when not using torch.compile (and some even with it) ...

Found some intermediates that weren't freed which should reduce VRAM usage overall, and modified RoPE application outside torch compile for similar gains than when using torch.compile.

2025-11-30 17:14:53 +02:00

..

configs

init

2025-02-25 20:03:08 +02:00

modules

Reduce peak VRAM usage when not using torch.compile (and some even with it)

2025-11-30 17:14:53 +02:00

radial_attention

support sparse sageattn2 for radial attn

2025-07-23 00:27:14 +03:00

schedulers

Fix TTM for dual sampler setups

2025-11-16 19:23:19 +02:00

LICENSE

Add alternative offloading method from Diffsynth

2025-03-02 14:37:08 +02:00

wan_video_vae.py

Use comfy core Conv3D workaround for VAE rather than the fp32 cast

2025-10-29 02:23:49 +02:00