# Ming-Image Design and Design-Layer two-stage deployment.
pipeline: ming_image
async_chunk: false

trust_remote_code: false
distributed_executor_backend: mp
dtype: bfloat16
enable_prefix_caching: false

stages:
  - stage_id: 0
    enforce_eager: true
    tensor_parallel_size: 1
    devices: "0"
    gpu_memory_utilization: 0.55
    max_num_seqs: 1
    output_connectors:
      to_stage_1: shared_memory_connector
    default_sampling_params:
      max_tokens: 1
      temperature: 0
      seed: 42

  - stage_id: 1
    enforce_eager: false
    diffusion_compile_granularity: regional
    diffusion_compile_dynamic: true
    tensor_parallel_size: 1
    devices: "1"
    max_num_seqs: 1
    input_connectors:
      from_stage_0: shared_memory_connector
    default_sampling_params:
      seed: 42

connectors:
  shared_memory_connector:
    name: SharedMemoryConnector

edges:
  - from: 0
    to: 1
    window_size: -1
    max_inflight: 1

platforms: {}