# MammothModa2 AR→DiT (text-to-image).

async_chunk: false
pipeline: mammoth_moda2

stages:
  - stage_id: 0
    devices: "0"
    max_num_seqs: 100
    max_model_len: 8192
    gpu_memory_utilization: 0.5
    enforce_eager: true
    trust_remote_code: true
    enable_prefix_caching: false

  - stage_id: 1
    devices: "0"
    max_num_seqs: 1
    gpu_memory_utilization: 0.3
    enforce_eager: true
    trust_remote_code: true
    enable_prefix_caching: false
    default_sampling_params:
      extra_args:
        text_guidance_scale: 9.0
        cfg_range: [0.0, 1.0]
        num_inference_steps: 50