# MOSS-TTS-Nano deploy: single-stage AR TTS (0.1B).
# Verified on 1x L4 24GB (and sufficient for H20 / A100 / 3090).
#
# Fields omitted from a stage fall back to StageDeployConfig defaults (see
# vllm_omni/config/stage_config.py). Notable choices:
#   * enforce_eager=true — the model uses upstream inference_stream() with
#     trust_remote_code; CUDA graph capture is not wired up.
#   * gpu_memory_utilization=0.3 — the AR LM + codec fit in ~2 GiB.
#   * max_num_seqs=4 — supports per-request streaming generators stored in
#     self._stream_gens.
#
# MOSS-TTS-Nano has no multimodal input preprocessing, so skip_mm_profiling
# bypasses the dummy-MM pass at profile time.
async_chunk: false
trust_remote_code: true

stages:
  - stage_id: 0
    max_num_seqs: 4
    gpu_memory_utilization: 0.3
    enforce_eager: true
    enable_prefix_caching: false
    max_num_batched_tokens: 4096
    max_model_len: 4096
    devices: "0"
    skip_mm_profiling: true
    default_sampling_params:
      temperature: 1.0
      top_p: 1.0
      top_k: 50
      max_tokens: 4096
      seed: 42