ltx: vae: implement chunked encoder + CPU IO chunking (Big VRAM reductions) (#13062)

Browse Source

* ltx: vae: add cache state to downsample block

* ltx: vae: Add time stride awareness to causal_conv_3d

* ltx: vae: Automate truncation for encoder

Other VAEs just truncate without error. Do the same.

* sd/ltx: Make chunked_io a flag in its own right

Taking this bi-direcitonal, so make it a for-purpose named flag.

* ltx: vae: implement chunked encoder + CPU IO chunking

People are doing things with big frame counts in LTX including V2V
flows. Implement the time-chunked encoder to keep the VRAM down, with
the converse of the new CPU pre-allocation technique, where the chunks
are brought from the CPU JIT.

* ltx: vae-encode: round chunk sizes more strictly

Only powers of 2 and multiple of 8 are valid due to cache slicing.

...

This commit is contained in:

rattus 2026-03-19 10:01:12 -07:00 committed by GitHub

parent fabed694a2

commit 6589562ae3

No known key found for this signature in database

GPG Key ID: B5690EEEBB952194

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Show Stats Download Patch File Download Diff File Expand all files Collapse all files

Diff Content Not Available