SolitaryThinker 345d2acb19 [fix]: init PackedExpertLinear params with zeros, not empty (review) ...

Addresses review thread on fastvideo/models/dits/magi_human.py:263. torch.empty leaves memory uninitialized; if a future caller skips load_state_dict or strict=False loses entries silently, the network would output NaNs. zero-init costs nothing at runtime (overwritten by load) and matches sibling MultiModalityRMSNorm which also uses torch.zeros.

2026-05-12 14:09:55 -07:00

..

audio

[Feat] Port LTX2 trainer (#1074)

2026-02-09 17:32:57 -08:00

camera

[feature] Add Hunyuan-GameCraft model support (#1071)

2026-02-14 08:07:44 +08:00

dits

[fix]: init PackedExpertLinear params with zeros, not empty (review)

2026-05-12 14:09:55 -07:00

encoders

[feat]: T5-Gemma encoder for MagiHuman pipeline (2/8) (#1296)

2026-05-12 13:59:55 -07:00

loader

[feat] Stable Audio Open 1.0: T2A + A2A + RePaint inpainting (native) (#1260)

2026-05-01 00:07:11 -07:00

schedulers

[feat] pre-commit support 120 col num (#1167)

2026-03-11 20:19:30 -07:00

upsamplers

[Feature] [Hy1.5] Support HY1.5 super-resolution pipeline for 1080p videos (#1046)

2026-02-05 16:39:20 -08:00

vaes

[feat] Stable Audio Open 1.0: T2A + A2A + RePaint inpainting (native) (#1260)

2026-05-01 00:07:11 -07:00

__init__.py

[Feature] Remove V1 folder (#642)

2025-07-24 22:43:12 -07:00

AGENTS.md

[docs] add hierarchical AGENTS.md per-directory guidance (#1278)

2026-05-02 03:28:18 -07:00

hf_transformer_utils.py

[Feature] Remove V1 folder (#642)

2025-07-24 22:43:12 -07:00

mask_utils.py

[New Model] Hunyuan1.5 (#943)

2025-12-21 00:57:52 -06:00

parameter.py

[Feature] Remove V1 folder (#642)

2025-07-24 22:43:12 -07:00

registry.py

[feat] Stable Audio Open 1.0: T2A + A2A + RePaint inpainting (native) (#1260)

2026-05-01 00:07:11 -07:00

utils.py

[feat] Add inference for MoE SF (#880)

2025-11-19 13:16:24 -08:00

vision_utils.py

[misc]: standardize install instructions on uv pip install (#1279)

2026-05-02 12:45:50 -07:00