Dong Wang 70c1dbc01e perf: run one-frame Wan VAE convolutions as 2D convolutions (#2038)

2026-09-24 00:23:31 +08:00

..

adapter

refactor: remove obsolete unused tensor filtering (#1984)

2026-09-18 23:41:37 +08:00

audio

feat: add Wan2.2 S2V (audio+img-to-video) support (#1925)

2026-09-13 23:33:50 +08:00

common

feat: add LLaDA-Image support (#1968)

2026-09-21 01:14:20 +08:00

detector

refactor: split ggml extensions and move implementations to cpp files (#1945)

2026-09-07 23:34:45 +08:00

diffusion

fix: add graph cuts for MiniMax-H3 text conditioning (#1900)

2026-09-24 00:03:29 +08:00

te

fix: avoid narrowing conversion in SigVQ patch embedding and format code

2026-09-21 01:27:31 +08:00

upscaler

refactor: unify model source and weight lifecycle management (#1956)

2026-09-10 23:53:48 +08:00

vae

perf: run one-frame Wan VAE convolutions as 2D convolutions (#2038)

2026-09-24 00:23:31 +08:00