# OpenAI-compatible FastH3 full-checkpoint server.
generator:
  model_path: FastVideo/FastVideo-Minimax-FastH3-Preview-v0.2
  engine:
    num_gpus: 4
    use_fsdp_inference: false
    parallelism:
      tp_size: 1
      sp_size: 4
    offload:
      dit: false
      dit_layerwise: false
      text_encoder: true
      image_encoder: true
      vae: true
      pin_cpu_memory: true
    compile:
      enabled: false
      vae_enabled: false
  pipeline:
    workload_type: t2v
    experimental:
      attention_backend: VIDEO_SPARSE_ATTN_H3
      VSA_sparsity: 0.9
      VSA_tile_size: 64
      inference_torch_compile: false
      vae_parallel_decode: true
      vae_parallel_decode_strategy: gather

server:
  host: 0.0.0.0
  port: 8000
  output_dir: outputs/openai_fasth3
  served_model_name: fasth3

default_request:
  negative_prompt: ""
  sampling:
    height: 768
    width: 1344
    num_frames: 124
    fps: 24
    num_inference_steps: 5
    guidance_scale: 1.0
    batch_cfg: false
    seed: 1000
  output:
    return_frames: false