hao-ai-lab-FastVideo

Files

T

vanch 384eee8aef feat(mlx): add FastH3-8-Step-V2 DMD schedule and thermal-safe MLX inference

- Support official 8-step DMD schedule from fastvideo_inference.json in MLX pipeline
- Implement MiniMaxH3SchedulerState.from_dmd_steps for exact sigma ladder calculation
- Add auto-detection of fastvideo_inference.json in checkpoint converter AdaLN precomputation
- Add inter_step_cooldown_s and per-step MLX graph/cache cleanup to prevent thermal throttling
- Support configurable VAE tile sizes to guarantee 256px tiled decode without grid artifacts
- Skip non-existent shard files gracefully in Qwen3-VL conditioner

2026-09-17 16:12:02 +08:00

checkpoint_conversion

feat(mlx): add FastH3-8-Step-V2 DMD schedule and thermal-safe MLX inference

2026-09-17 16:12:02 +08:00

dataset_preparation

[misc] yapf pass under CI's interpreter (3.12) + pin hook language_version (#1702 )

2026-08-08 22:24:17 -07:00

distill

[bugfix] [misc] Use training_state_checkpointing_steps in scripts/ (#846 )

2025-10-19 20:20:53 -07:00

finetune

[Misc] clean up VSA finetuning examples. (#1111 )