vllm-omni/vllm_omni/deploy/mimo_audio.yaml

# MiMo Audio deploy: 2-stage thinker+talker → code2wav.
#
# Default mode is async-chunk streaming on a single GPU (both stages on
# device 0) through SharedMemoryConnector. For the legacy 2-GPU sync
# pipeline (stage 1 on a second card), pass ``--no-async-chunk
# --stage-1-devices 1 --stage-1-max-model-len 18192
# --stage-1-max-num-batched-tokens 18192`` to the serve CLI.
async_chunk: true
dtype: bfloat16

connectors:
  connector_of_shared_memory:
    name: SharedMemoryConnector
    extra:
      shm_threshold_bytes: 365536
      codec_streaming: true
      connector_get_sleep_s: 0.001
      connector_get_max_wait_first_chunk: 3000
      connector_get_max_wait: 300
      codec_chunk_frames: 3
      codec_left_context_frames: 3

stages:
  - stage_id: 0
    max_num_seqs: 1
    gpu_memory_utilization: 0.5
    enforce_eager: true
    trust_remote_code: true
    enable_prefix_caching: 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: 0.6
      top_p: 0.95
      top_k: 50
      max_tokens: 18192
      seed: 42
      repetition_penalty: 1.1

  - stage_id: 1
    max_num_seqs: 1
    gpu_memory_utilization: 0.3
    enforce_eager: true
    trust_remote_code: 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: 18192
      seed: 42