ComfyUI/comfy/ldm/lightricks/vae
rattus 82b868a45a
Fix VRAM leak in tiler fallback in video VAEs (#13073)
* sd: soft_empty_cache on tiler fallback

This doesnt cost a lot and creates the expected VRAM reduction in
resource monitors when you fallback to tiler.

* wan: vae: Don't recursion in local fns (move run_up)

Moved Decoder3d’s recursive run_up out of forward into a class
method to avoid nested closure self-reference cycles. This avoids
cyclic garbage that delays garbage of tensors which in turn delays
VRAM release before tiled fallback.

* ltx: vae: Don't recursion in local fns (move run_up)

Mov the recursive run_up out of forward into a class
method to avoid nested closure self-reference cycles. This avoids
cyclic garbage that delays garbage of tensors which in turn delays
VRAM release before tiled fallback.
2026-03-19 22:30:27 -04:00
..
audio_vae.py Support the LTXAV 2.3 model. (#12773) 2026-03-04 20:06:20 -05:00
causal_audio_autoencoder.py Support the LTXAV 2.3 model. (#12773) 2026-03-04 20:06:20 -05:00
causal_conv3d.py ltx: vae: implement chunked encoder + CPU IO chunking (Big VRAM reductions) (#13062) 2026-03-19 09:58:47 -07:00
causal_video_autoencoder.py Fix VRAM leak in tiler fallback in video VAEs (#13073) 2026-03-19 22:30:27 -04:00
conv_nd_factory.py Support LTXV 0.9.5. 2025-03-05 00:13:49 -05:00
dual_conv3d.py Support LTXV 0.9.5. 2025-03-05 00:13:49 -05:00
pixel_norm.py Support Lightricks LTX-Video model. 2024-11-22 08:46:39 -05:00