# Ming-flash-omni-2.0 standalone TTS deploy: talker only.
#
# Single-stage configuration for direct text -> audio synthesis
# The talker runs as a generation worker on a single GPU
# and owns the tokenizer.
pipeline: ming_flash_omni_tts
async_chunk: false

trust_remote_code: true
enable_prefix_caching: false

stages:
  - stage_id: 0
    max_num_seqs: 1
    gpu_memory_utilization: 0.8
    enforce_eager: true
    max_num_batched_tokens: 100000
    devices: "0"
    default_sampling_params:
      temperature: 0.0
      max_tokens: 1

# Ming-flash-omni-2.0 has only been verified on CUDA devices
platforms: {}