Files
hao-ai-lab-FastVideo/examples/serving/mlx_fasth3_8step.yaml

27 lines
705 B
YAML

# Native MLX FastH3 8-Step V2 server. Convert the DiT with --include-vsa first.
runtime: mlx
generator:
model_path: FastVideo/FastVideo-FastH3-8-Step-V2
model_root: ./FastH3-8-Step-V2
mlx_checkpoint: ./FastH3-8-Step-V2-MLX/int8
prompt_cache_dir: ./outputs/h3_prompt_cache
vae_dtype: fp32
vsa: true
vsa_sparsity: 0.8
vsa_tile_size: 64
server:
host: 127.0.0.1
port: 8000
served_model_name: fasth3
output_dir: outputs/mlx_fasth3_8step
default_request:
sampling:
height: 480
width: 832
num_frames: 124
fps: 24
# HTTP convention: nine sigma points, eight DiT forwards. Native MLX uses num_steps=8.
num_inference_steps: 9
guidance_scale: 1.0
seed: 2026