akleine 2891378bb1 fix: prevent core dump in CPU backend if using FP8 (e4m3) tensors (#2140)

2026-10-15 22:26:27 +08:00

..

adapter

fix: preserve singleton output dimension when merging LoRA (#2116)

2026-10-10 01:12:03 +08:00

audio

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

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

common

fix: prevent core dump in CPU backend if using FP8 (e4m3) tensors (#2140)

2026-10-15 22:26:27 +08:00

detector

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

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

diffusion

feat: run conditional and unconditional CFG in one batched UNet forward (#2085)

2026-10-10 23:35:58 +08:00

te

fix: load INT8 convrot LLM embeddings correctly (#2067)

2026-09-27 19:46:21 +08:00

upscaler

feat: add MoSR upscaler support (#2128)

2026-10-12 22:38:38 +08:00

vae

feat: add TAEQI2.1 support for Qwen Image 2.1 (#2123)

2026-10-11 00:01:18 +08:00