SolitaryThinker b0f1b8ad96 [feat]: Cosmos3 DiT skeleton (Cosmos3VFMTransformer + Cosmos3LanguageModel) ...

Ports math (compute_mrope_position_ids_text/_vision, patchify, unpatchify) verbatim from vllm-omni transformer_cosmos3.py:113-177,1009-1036. Module tree (language_model.layers.*.self_attn.{q,k,v,o}_proj + gen_layers.*.cross_attention.* + vae2llm + llm2vae + time_embedder + norm_moe_gen) exposes the parameter names the checkpoint converter targets. All layer forward() raise NotImplementedError until weights publish; module instantiation + state-dict key tests pass.

2026-07-20 12:18:53 -07:00

..

hyworld

[feat] Add Kandinsky-5 T2V/I2V pipeline support (#1471)

2026-07-07 14:43:30 -07:00

lingbotworld

[Refactor] SP Mask --> original seq len; HunyuanVideo 1.5 does not need mask (#1142)

2026-03-04 11:44:47 +08:00

lingbotworld2

[new-model] Port LingBot-World-v2 (#1579)

2026-07-16 19:51:53 -07:00

matrixgame2

[feat] World model training using third person games (#1443)

2026-07-10 05:09:07 +00:00

matrixgame3

[feat] Add MatrixGame3.0 (#1201)

2026-05-27 21:07:01 +00:00

__init__.py

[docs]: modernize documentation build (#1503)

2026-06-28 02:02:09 -07:00

_relative_rope.py

[feat] Relativistic RoPE re-indexing for long causal rollouts (#1454)

2026-06-28 01:43:00 -07:00

base.py

[Misc] Remove Teacache (#1121)

2026-02-22 16:53:07 -08:00

causal_wanvideo.py

[feat] World model training using third person games (#1443)

2026-07-10 05:09:07 +00:00

cosmos2_5.py

[feat] Add Cosmos 2.5 T2W training pipeline (LoRA + full fine-tune) (#1227)

2026-05-11 19:15:00 -07:00

cosmos3.py

[feat]: Cosmos3 DiT skeleton (Cosmos3VFMTransformer + Cosmos3LanguageModel)

2026-07-20 12:18:53 -07:00

cosmos.py

[feat] Cosmos 2.5 training support in fastvideo.train (#1224)

2026-05-01 01:15:02 +00:00

dreamx_world_ar.py

[feat] Add DreamX-World 5B Cam and AR pipelines (#1538)

2026-07-07 06:16:18 +00:00

dreamx_world.py

[feat] Add DreamX-World 5B Cam and AR pipelines (#1538)

2026-07-07 06:16:18 +00:00

flux_2.py

[model] Flux2 Klein Port (#1349)

2026-06-09 14:55:55 -07:00

flux.py

[feat] Fix FLUX.1-dev port: native RoPE, parity tests, SSIM reference (#1321)

2026-07-13 01:49:42 -07:00

gen3c.py

[feat] add gen3c (cosmos-7b) model and pipeline support (#1059)

2026-04-01 11:42:02 +00:00

glm_image.py

[feat] Add GLM-Image inference support (#1030)

2026-07-12 22:42:42 -07:00

hunyuangamecraft.py

[Misc] Remove Teacache (#1121)

2026-02-22 16:53:07 -08:00

hunyuanvideo15.py

[feat] Add Kandinsky-5 T2V/I2V pipeline support (#1471)

2026-07-07 14:43:30 -07:00

hunyuanvideo.py

[Refactor] SP Mask --> original seq len; HunyuanVideo 1.5 does not need mask (#1142)

2026-03-04 11:44:47 +08:00

kandinsky5.py

[feat] Add Kandinsky-5 T2V/I2V pipeline support (#1471)

2026-07-07 14:43:30 -07:00

lingbot_video.py

[new-model] Add LingBot-Video Dense and MoE/refiner T2V inference (#1595)

2026-07-18 20:18:16 -07:00

longcat.py

[feat]: add LongCat bidirectional finetuning support (#1244)

2026-05-09 12:20:43 -07:00

ltx2.py

[bugfix]: keep LTX2 rms_norm outputs bf16 under torch 2.12 autocast (#1587)

2026-07-13 16:04:21 -07:00

magi_human.py

[feat]: MagiHuman DiT (transformer) port + parity tests (3/8) (#1297)

2026-05-12 14:49:03 -07:00

sd3.py

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

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

stable_audio.py

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

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

wanvideo.py

[feat] Add AnyFlow any-step video distillation (pretrain + on-policy) (#1371)

2026-07-12 02:32:08 +00:00

zimage.py

[fix] Z-Image (#1236) draft port: rebase + strict-load contract + bf16 encoder parity + PORT_STATUS (#1339)

2026-07-16 18:18:25 -07:00