# Step-Audio2 deploy: thinker -> token2wav with async chunk streaming.
async_chunk: true
trust_remote_code: true
enable_prefix_caching: false

stages:
  - stage_id: 0
    devices: "0,1"
    tensor_parallel_size: 2
    max_num_seqs: 1
    gpu_memory_utilization: 0.7
    enforce_eager: true
    async_scheduling: false
    max_num_batched_tokens: 1024
    default_sampling_params:
      temperature: 0.7
      top_p: 0.9
      top_k: -1
      max_tokens: 1024
      seed: 42
      repetition_penalty: 1.05

  - stage_id: 1
    devices: "1"
    max_num_seqs: 1
    gpu_memory_utilization: 0.2
    enforce_eager: true
    async_scheduling: false
    max_num_batched_tokens: 2048
    hf_overrides:
      architectures: ["StepAudio2Token2WavForConditionalGeneration"]
    default_sampling_params:
      temperature: 0.0
      top_p: 1.0
      top_k: -1
      max_tokens: 1
      seed: 42