# Qwen3-TTS deploy: talker → code2wav via shared-memory chunk streaming.
# Verified on 1x H100.
#
# Fields omitted from a stage fall back to StageDeployConfig defaults (see
# vllm_omni/config/stage_config.py). Notable choices for this model:
#   * Stage 0 (talker) sets max_num_batched_tokens=512 for async-chunk
#     latency tuning (not correctness) — small per-step batches keep
#     first-chunk latency low.
#   * Stage 1 (code2wav) sets max_num_batched_tokens=65536 for correctness:
#     codec prefill length (Q * num_frames) exceeds the 32k default.
#   * Stage 0 does not set enforce_eager — talker runs cudagraph by default.
#     Stage 1 defaults to false so Code2Wav can use its inner cudagraph;
#     set true to disable that path in eager mode. NPU platform flips stage 0 to true where
#     cudagraph is not yet verified.
async_chunk: true

connectors:
  connector_of_shared_memory:
    name: SharedMemoryConnector
    extra:
      shm_threshold_bytes: 65536
      codec_streaming: true
      connector_get_sleep_s: 0.01
      connector_get_max_wait_first_chunk: 3000
      connector_get_max_wait: 300
      # Must match the decoder sliding attention window.
      codec_chunk_frames: 25
      codec_left_context_frames: 72
      # Emit only the first audio chunk early, then return to codec_chunk_frames.
      initial_codec_chunk_frames: 1
      # Common Stage1 decode buckets:
          #   no-ref first/steady chunks: 25 / 97 frames
          #   Base ref-context first/steady chunks: 73 / 169 frames
          #   decoder internal non-streaming chunks: 325 frames
      decode_cudagraph_capture_sizes: [25, 73, 97, 169, 325]

stages:
  - stage_id: 0
    max_num_seqs: 10
    gpu_memory_utilization: 0.3
    trust_remote_code: true
    # Prefix caching on by default. The HS opt-out (talker only consumes the
    # last token's hidden state) and deferred mm-output writes added in this
    # PR make per-step bookkeeping negligible, and any text repetition across
    # requests (same voice or shared ref_audio) is a net throughput win.
    # Disable explicitly if memory headroom is tight on a single-GPU deploy.
    enable_prefix_caching: true
    async_scheduling: true
    max_num_batched_tokens: 512
    max_model_len: 4096
    devices: "0"
    output_connectors:
      to_stage_1: connector_of_shared_memory
    default_sampling_params:
      temperature: 0.9
      top_k: 50
      max_tokens: 4096
      seed: 42
      repetition_penalty: 1.05
    subtalker_sampling_params:
      do_sample: true
      temperature: 0.9
      top_k: 50
      top_p: 1.0

  - stage_id: 1
    max_num_seqs: 10
    gpu_memory_utilization: 0.3
    enforce_eager: false
    trust_remote_code: true
    enable_prefix_caching: false
    async_scheduling: true
    # Must be divisible by num_code_groups and cover (left_context + chunk).
    # Prefill length is Q * num_frames (e.g. 16 * 2148 = 34368); keep
    # headroom past 32k.
    max_num_batched_tokens: 65536
    # async_chunk appends windows per step; max_model_len must cover the
    # accumulated flat codec stream.
    max_model_len: 65536
    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

platforms:
  npu:
    stages:
      - stage_id: 0
        enforce_eager: true