# Step-Audio2 ASR deploy: thinker only.
pipeline: step_audio_2_asr
async_chunk: false
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: 0.8
    enforce_eager: true
    async_scheduling: false
    max_num_batched_tokens: 2048
    default_sampling_params:
      temperature: 0.7
      top_p: 0.9
      top_k: -1
      max_tokens: 1024
      seed: 42
      repetition_penalty: 1.05