Mingjia Huo 63030cf6ec [fix] Fix causal self-forcing attention settings (#1355)

2026-05-17 22:59:47 -07:00

..

__init__.py

[misc]: empty __init__.py files with no logic (#1346)

2026-05-13 13:09:40 -07:00

builder.py

[feat] Refactor training framework into fastvideo/train (#1159)

2026-03-09 15:16:42 -07:00

checkpoint.py

[refactor] train v1 clean up

2026-03-09 18:58:56 -07:00

config.py

[fix] Fix causal self-forcing attention settings (#1355)

2026-05-17 22:59:47 -07:00

dataloader.py

[misc] Rename MatrixGame to MatrixGame2 (#1357)

2026-05-17 22:57:03 -07:00

instantiate.py

[feat] Refactor training framework into fastvideo/train (#1159)

2026-03-09 15:16:42 -07:00

lora.py

[feat] Add minimal LoRA finetuning support to the YAML training stack (#1242)

2026-05-17 14:49:13 -07:00

module_state.py

[feat] Refactor training framework into fastvideo/train (#1159)

2026-03-09 15:16:42 -07:00

moduleloader.py

[feat] Self-Forcing methods in refactored training infra (#1164)

2026-03-09 20:20:59 -07:00

negative_prompt.py

[bugfix]: fix SP deadlock in negative prompt encoding during training (#1178)

2026-04-28 01:06:49 +00:00

optimizer.py

[feat] Refactor training framework into fastvideo/train (#1159)

2026-03-09 15:16:42 -07:00

tracking.py

[feat] Refactor training framework into fastvideo/train (#1159)

2026-03-09 15:16:42 -07:00

training_config.py

[refactor] train v1 clean up

2026-03-09 18:58:56 -07:00