# MOSS-TTS-Local-Transformer-v1.5 (MossTTSLocalModel, n_vq=12, 48 kHz stereo)
# HF: OpenMOSS-Team/MOSS-TTS-Local-Transformer-v1.5
# Codec: OpenMOSS-Team/MOSS-Audio-Tokenizer-v2 (48 kHz, stereo, channel-interleaved RVQ)
# Uses a 1-layer GPT2-style local depth transformer (no delay warm-up), reset every
# frame — same per-frame timing (80 ms/frame, 12.5 fps) as MOSS-TTS-Realtime.
async_chunk: true

connectors:
  shm:
    name: SharedMemoryConnector
    extra:
      connector_get_sleep_s: 0.005
      connector_get_max_wait_first_chunk: 1000
      connector_get_max_wait: 300
      initial_codec_chunk_frames: 1   # 1 frame * 80 ms/frame = 80 ms first audio chunk
      codec_chunk_frames: 15          # 15 frames * 80 ms/frame = 1.2 s steady chunks
      codec_left_context_frames: 0

stages:
  - stage_id: 0
    max_num_seqs: 64
    gpu_memory_utilization: 0.60
    enable_prefix_caching: false
    async_scheduling: true
    max_num_batched_tokens: 65536
    max_model_len: 4096
    devices: "0"
    # profiler_config:
    #   profiler: torch
    #   torch_profiler_dir: /root/vllm-omni-workspace/vllm-omni/results/moss_local_stage0/batch_8
    output_connectors:
      to_stage_1: shm
    default_sampling_params:
      temperature: 1.7
      top_p: 0.8
      top_k: 25
      max_tokens: 4096
      seed: 42
      repetition_penalty: 1.0

  - stage_id: 1
    max_num_seqs: 64
    gpu_memory_utilization: 0.30
    enforce_eager: false
    enable_prefix_caching: false
    async_scheduling: true
    compilation_config:
      # Reused by the codec as execution-batch buckets; T is derived from
      # initial_codec_chunk_frames and codec_chunk_frames.
      cudagraph_capture_sizes: [1, 2, 4, 8, 16, 32, 64]
      cudagraph_num_of_warmups: 1
    # profiler_config:
    #   profiler: torch
    #   torch_profiler_dir: /root/vllm-omni-workspace/vllm-omni/results/moss_local_stage1/batch_8
    max_num_batched_tokens: 65536
    max_model_len: 65536
    devices: "0"
    input_connectors:
      from_stage_0: shm
    default_sampling_params:
      temperature: 0.0
      top_p: 1.0
      top_k: -1
      max_tokens: 65536
      seed: 42
      repetition_penalty: 1.0