-
Notifications
You must be signed in to change notification settings - Fork 251
Pull requests: ModelTC/LightX2V
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
fix: transcode non-AAC audio to AAC for MP4 container
#1357
opened Aug 10, 2026 by
Tingting-Y
Collaborator
Loading…
4 tasks done
feat(hunyuan-image3): add multi-micro hybrid parallelism
#1350
opened Aug 10, 2026 by
Chernobyllight
Contributor
Loading…
feat(thor): add FA4 and stride-based split-N NVFP4 support for Wan2.2
#1344
opened Aug 10, 2026 by
Michael20070814
Contributor
Loading…
feat(hunyuan3d): profile paint model inference
#1343
opened Aug 8, 2026 by
Watebear
Collaborator
Loading…
feat(flux2/metax): optimize distributed encoder and decoder，tp8 pipeline 53.99s-> 20.23s on metax platform
#1342
opened Aug 8, 2026 by
Watebear
Collaborator
Loading…
feat(qwen-image/metax): optimize distributed offload，metax cfg2_sp4 pipeline cost 52.76s-> 21.68s
#1341
opened Aug 8, 2026 by
Watebear
Collaborator
Loading…
Optimize Ulysses FP8 pre-quant row tiling
#1304
opened Jul 28, 2026 by
STwangyingrui
Contributor
Loading…
Inference Sparse Optimization of Wan2.2 on Ascend Platform
#1301
opened Jul 27, 2026 by
Watebear
Collaborator
Loading…
Optimize offload weight pinning with mmap host registration
#1206
opened Jul 1, 2026 by
Fatemanx
Contributor
Loading…
perf: improve HunyuanVideo1.5 I2V runtime and VAE decode controls
#1201
opened Jun 30, 2026 by
starrkk
Loading…
perf: optimize Hunyuan DiT Ulysses and non-attention paths
#1200
opened Jun 30, 2026 by
starrkk
Loading…
feat(npu): Perform inference with sparse FA and NPU fusion operators on Ascend NPU
#1159
opened Jun 17, 2026 by
liaopingbo
Contributor
Loading…
ProTip!
Updated in the last three days: updated:>2026-08-09.