hao-ai-lab-FastVideo

test_dmd_sampling.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_frame_upsample.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_import_laziness.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_memory_limits.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_mlx_affine_dq_gemm.py

[perf]: dispatch wide-M affine H3 MLX linears through dequant plus dense GEMM (#1788 )

2026-08-30 14:42:01 -07:00

test_mlx_checkpoint_compat.py

[bugfix] FastMetal-QAD MLX support: refuse CUDA QAD trees, use packed mlx_dit config, stream loads (#1736 ) (#1758 )

2026-08-25 14:51:40 -07:00

test_mlx_checkpoint.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_mlx_compile_parity.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_mlx_diffusers_compile_dispatch.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_mlx_dit_parity.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_mlx_fast_spatial.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_mlx_fastwan_benchmark.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_mlx_minimax_h3_8step_schedule.py

[feat]: add a narrow FastH3 8-step MLX ladder

2026-09-23 11:06:55 -07:00

test_mlx_minimax_h3_conditioner.py

[perf] Speed up exact MiniMax H3 MLX inference (#1792 )

2026-08-31 04:14:55 -07:00

test_mlx_minimax_h3_fast_mode.py

[bugfix]: allow MiniMax H3 frame padding at the 15-second limit

2026-09-14 16:54:41 -07:00

test_mlx_minimax_h3_fast_spatial.py

[feat] Add an optional MLX TAEH3 preview decoder (#1794 )

2026-08-31 05:08:06 -07:00

test_mlx_minimax_h3_modulation.py

[perf] Speed up exact MiniMax H3 MLX inference (#1792 )

2026-08-31 04:14:55 -07:00

test_mlx_minimax_h3_parity.py

[feat] Add MiniMax H3 MLX T2VA inference (#1770 )

2026-08-28 12:54:33 -07:00

test_mlx_minimax_h3_vsa_regressions.py

[feat] Add an optional MLX TAEH3 preview decoder (#1794 )

2026-08-31 05:08:06 -07:00

test_mlx_minimax_h3_vsa.py

[perf] Add MiniMax H3 MLX VSA and SIMD attention (#1776 )

2026-08-30 13:44:54 -07:00

test_mlx_minimax_h3_weight_reads.py

[perf] Speed up exact MiniMax H3 MLX inference (#1792 )

2026-08-31 04:14:55 -07:00

test_mlx_prompt_enhance.py

[bugfix] Fix MLX prompt enhancement sampler compatibility (#1891 )

2026-09-27 14:53:25 -07:00

test_mlx_prompt_to_video_decode.py

[bugfix] FastMetal-QAD MLX support: refuse CUDA QAD trees, use packed mlx_dit config, stream loads (#1736 ) (#1758 )

2026-08-25 14:51:40 -07:00

test_mlx_refine.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_mlx_rife_interpolation.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_mlx_taeh3.py

[feat] Add an optional MLX TAEH3 preview decoder (#1794 )

2026-08-31 05:08:06 -07:00

test_mlx_taehv_parity.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_mlx_wan22_memory_handoff.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_mlx_wan22_parity.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_mlx_wan22_prompt_cache_fingerprint.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_mlx_wan22_real_weights_parity.py

[refactor] Simplify Wan sampling and tests (#1825 )

2026-09-07 15:57:19 -07:00

test_mlx_wan_vae_denormalization.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_quant_backends.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_quant_capability.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_taehv_decode.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_wan22_sample.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

test_windowed_attention.py

[feat]: Apple Silicon MLX runtime — INT8 Wan2.1 and Wan2.2 inference (#1638 )

2026-08-18 15:08:00 -07:00

tiny_h3.py

[feat] Add MiniMax H3 MLX T2VA inference (#1770 )

2026-08-28 12:54:33 -07:00

tiny_wan.py

[refactor] Simplify Wan sampling and tests (#1825 )

2026-09-07 15:57:19 -07:00