# Ming-omni-tts deploy: stage-0 LLM+flow -> stage-1 audio VAE.
# Verified legacy settings migrated from ming_tts.yaml and ming_tts_async_chunk.yaml.
# Default mode is async-chunk streaming on a single GPU.
# pipeline: required — HF config reports model_type="dense" with no architectures,
# so auto-detection falls through. This key routes the deploy-config probe in
# StageConfigFactory.create_from_model to the correct registry entry.
pipeline: ming_tts
async_chunk: true
trust_remote_code: false
dtype: bfloat16
enable_prefix_caching: false

connectors:
  connector_of_shared_memory:
    name: SharedMemoryConnector
    extra:
      latent_chunk_size: 25
      initial_latent_chunk_size: 4
      latent_left_context: 0

stages:
  - stage_id: 0
    max_num_seqs: 1
    gpu_memory_utilization: 0.45
    enforce_eager: true
    enable_prefix_caching: false
    async_scheduling: false
    max_num_batched_tokens: 8192
    max_model_len: 8192
    devices: "0"
    output_connectors:
      to_stage_1: connector_of_shared_memory
    default_sampling_params:
      temperature: 0.0
      top_p: 1.0
      top_k: -1
      max_tokens: 512
      detokenize: true

  - stage_id: 1
    max_num_seqs: 1
    gpu_memory_utilization: 0.25
    enforce_eager: true
    enable_prefix_caching: false
    async_scheduling: false
    max_num_batched_tokens: 8192
    max_model_len: 8192
    devices: "0"
    input_connectors:
      from_stage_0: connector_of_shared_memory
    default_sampling_params:
      temperature: 0.0
      top_p: 1.0
      top_k: -1
      max_tokens: 1
      detokenize: false