Skip to content

Conversation

@pull
Copy link

@pull pull bot commented Jan 24, 2026

See Commits and Changes for more details.


Created by pull[bot] (v2.0.0-alpha.4)

Can you help keep this open source service alive? 💖 Please sponsor : )

comfyanonymous and others added 2 commits January 23, 2026 19:50
* ops: introduce autopad for conv3d

This works around pytorch missing ability to causal pad as part of the
kernel and avoids massive weight duplications for padding.

* wan-vae: rework causal padding

This currently uses F.pad which takes a full deep copy and is liable to
be the VRAM peak. Instead, kick spatial padding back to the op and
consolidate the temporal padding with the cat for the cache.

* wan-vae: implement zero pad fast path

The WAN VAE is also QWEN where it is used single-image. These
convolutions are however zero padded 3d convolutions, which means the
VAE is actually just 2D down the last element of the conv weight in
the temporal dimension. Fast path this, to avoid adding zeros that
then just evaporate in convoluton math but cost computation.
@pull pull bot locked and limited conversation to collaborators Jan 24, 2026
@pull pull bot added the ⤵️ pull label Jan 24, 2026
@pull pull bot merged commit 4e6a1b6 into code:master Jan 24, 2026
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants