Ethanfel 615599cdfd Optimize merge node RAM usage with pre-allocation and context slicing ...

Replace torch.cat with pre-allocated tensor + in-place copy.
Clone only small context slices for blending instead of holding
full source/vace tensors during the blend loop.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-02-21 16:51:24 +01:00

7.4 KiB

Raw Blame History

View Raw