# Audio8 TTS Preview 0.6B deploy: async-chunk streaming slow_ar -> codec_decoder.
# Model: Audio8/Audio8-TTS-Preview-0.6b (model_type = "arktts").
#
# trust_remote_code is deliberately OFF: the checkpoint ships an `auto_map`, and
# transformers prefers remote code over registered classes when it is enabled,
# which would bypass vllm-omni's Audio8TTSConfig (the Qwen2-shaped view that
# Qwen2Model needs). The tokenizer is a plain PreTrainedTokenizerFast and needs
# no remote code either.
async_chunk: true
enable_chunked_prefill: false

connectors:
  connector_of_shared_memory:
    name: SharedMemoryConnector
    extra:
      codec_streaming: true
      connector_get_sleep_s: 0.01
      connector_get_max_wait_first_chunk: 3000
      connector_get_max_wait: 300
      # ~21.5 Hz codec; 25 frames ~= 1.16 s of audio.
      codec_chunk_frames: 25
      codec_left_context_frames: 25
      initial_codec_chunk_frames: 4
      # float32 keeps the Snake activations / weight-normed convs clean.
      audio8_tts_codec_dtype: float32

stages:
  - stage_id: 0
    # >= 4 so concurrent requests pipeline; a default of 1 starves the codec
    # window and produces audible gaps under load.
    #
    # Measured on 1x H20 (20 prompts, mean audio 4.5 s): at client concurrency 8,
    # raising this to 8 buys +27% throughput and 4.5x lower first-packet latency
    # (1124 ms -> 247 ms) at the cost of a 0.22 s worst-case buffer deficit in
    # 1 of 20 requests. 4 is the default because every measured point here had
    # zero underrun; see examples/online_serving/text_to_speech/README.md.
    max_num_seqs: 4
    # 0.6B weights + a 2048-token KV cache need very little: sized for a small
    # slice of the GPU so the codec stage and other tenants still fit.
    gpu_memory_utilization: 0.2
    enforce_eager: false
    trust_remote_code: false
    enable_prefix_caching: false
    async_scheduling: false
    # The checkpoint's max_seq_len is 2048 packed text+audio positions; with
    # chunked prefill off, max_num_batched_tokens must be >= max_model_len.
    max_model_len: 2048
    max_num_batched_tokens: 2048
    devices: "0"
    output_connectors:
      to_stage_1: connector_of_shared_memory
    default_sampling_params:
      # generation_config.json of the released checkpoint.
      temperature: 0.7
      top_k: 50
      top_p: 0.9
      max_tokens: 1024
      seed: 42
      repetition_penalty: 1.0

  - stage_id: 1
    max_num_seqs: 1
    # The codec is ~1.4 GB of weights plus per-chunk activations.
    gpu_memory_utilization: 0.1
    enforce_eager: true
    trust_remote_code: false
    enable_prefix_caching: false
    async_scheduling: false
    max_model_len: 2048
    max_num_batched_tokens: 2048
    devices: "0"
    input_connectors:
      from_stage_0: connector_of_shared_memory
    default_sampling_params:
      temperature: 0.0
      top_p: 1.0
      top_k: -1
      max_tokens: 65536
      seed: 42
      repetition_penalty: 1.0