-
Notifications
You must be signed in to change notification settings - Fork 766
Pull requests: Lightricks/LTX-2
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fix: apply per-tensor weight scales during FP8 dequantization
#172
opened Mar 22, 2026 by
Julio G (sumurtk2)
Loading…
Add @torch.inference_mode() to pipeline __call__ methods
#170
opened Mar 19, 2026 by
garrick99
Loading…
feat(pipelines): add optional model instance caching to ModelLedger
#118
opened Feb 14, 2026 by
Benjamin Cowen (BenCowen)
Loading…
Fix modulo operator in help text for skip step
#103
opened Feb 3, 2026 by
Sahiru Wijesinghe (sahiruw)
Loading…
Free Gemma text encoder after caption embedding to reduce VRAM during training
#85
opened Jan 21, 2026 by
bruefire (bruefire)
Loading…
Bugfix: fix memory allocation issues during multi-GPU training
#67
opened Jan 14, 2026 by
LittleNyima (LittleNyima)
Loading…
8Gb Vram optimized, Win11 support + Web UI + optimized transformer +40% more frames on 8Gb
#66
opened Jan 14, 2026 by
nalexand
Loading…
feat: Add deterministic inference pipeline for reproducible video generation
#28
opened Jan 8, 2026 by
q5sys (JT) (q5sys)
Loading…
ProTip!
no:milestone will show everything without a milestone.