#   FASTVIDEO_ATTENTION_BACKEND=ATTN_QAT_INFER FASTVIDEO_VSA_SM100A=0 FASTVIDEO_FA4=0 \
#     FLASHINFER_CUDA_ARCH_LIST=12.0a FASTVIDEO_STAGE_LOGGING=1 \
#     fastvideo generate --config examples/inference/basic/basic_compacth3_rtx5090.yaml
generator:
  model_path: ./CompactH3
  engine:
    num_gpus: 1
    use_fsdp_inference: false
    quantization:
      transformer_quant: NVFP4
      layer_profile: h3_dit
    parallelism:
      tp_size: 1
      sp_size: 1
    offload:
      dit: false
      dit_layerwise: false
      text_encoder: true
      vae: false
      pin_cpu_memory: true
      lazy_module_load: false
    compile:
      enabled: false
      vae_enabled: false
  pipeline:
    experimental:
      attention_backend: ATTN_QAT_INFER
      h3_sequential_load: true
      inference_torch_compile: false
      vae_parallel_decode: false
      video_decode_backend: h3-vae
request:
  prompt: >-
    A wide cinematic shot of an alpine meadow at sunrise, pale pink mountain
    peaks above a blue valley filled with thin morning mist.
  negative_prompt: ""
  sampling:
    seed: 2026
    height: 480
    width: 832
    num_frames: 124
    fps: 24
    num_inference_steps: 5
    guidance_scale: 1.0
    batch_cfg: false
  output:
    output_path: outputs/compacth3_rtx5090/
    save_video: true
    return_frames: false