# dots.tts deployment config (single-stage AR talker).
#
# Conservative first-integration settings: eager execution, no CUDA
# Graphs, no batched side-path optimizations yet — see voxcpm2.yaml for
# the runtime knobs a mature deployment of this model family grows.
#
# Verified locally on RTX 5080 16GB.

async_chunk: false
dtype: bfloat16

stages:
  - stage_id: 0
    max_num_seqs: 4
    gpu_memory_utilization: 0.8
    enforce_eager: true
    trust_remote_code: true
    enable_prefix_caching: false
    async_scheduling: true
    max_num_batched_tokens: 4096
    max_model_len: 4096
    devices: "0"
    default_sampling_params:
      temperature: 0.0
      top_p: 1.0
      top_k: -1
      max_tokens: 4096
      repetition_penalty: 1.0