# Higgs-audio v2 deploy: Stage 0 (talker) -> Stage 1 (code2wav) via shared memory.
#
# Phase-1 scope is plain text -> 24 kHz speech only; voice cloning, multi-speaker,
# ChatML rich messages, and music/sound-event prompts are rejected by the
# request validator with explicit 4xx (see
# vllm_omni/entrypoints/openai/serving_speech.py and
# vllm_omni/model_executor/models/higgs_audio_v2/higgs_audio_v2_tokenizer.py).
#
# Streaming is wired through the stage-input processor's async-chunk
# callback, the shared-memory connector ``codec_streaming`` flag, and the
# WAV/PCM streaming convention in serving_speech.py. To run a strictly
# non-streaming smoke test, set ``codec_streaming: false`` in the connector
# extras below.
async_chunk: false

connectors:
  connector_of_shared_memory:
    name: SharedMemoryConnector
    extra:
      codec_streaming: true
      connector_get_sleep_s: 0.01
      connector_get_max_wait_first_chunk: 5000
      connector_get_max_wait: 500
      codec_chunk_frames: 25
      codec_left_context_frames: 25
      initial_codec_chunk_frames: 1

stages:
  - stage_id: 0
    max_num_seqs: 4
    gpu_memory_utilization: 0.6
    # Disable cudagraph capture: the live audio-sampler dispatch is still
    # iterating, and the host's flash-attn-hopper graph path tripped a CUDA
    # driver vs runtime mismatch during capture on this image.
    enforce_eager: true
    trust_remote_code: true
    enable_prefix_caching: false
    async_scheduling: false
    max_num_batched_tokens: 2048
    # max_model_len covers prompt + max_new_tokens. Up to ~1500 codec
    # frames per request fit comfortably under 4096.
    max_model_len: 4096
    devices: "0"
    output_connectors:
      to_stage_1: connector_of_shared_memory
    default_sampling_params:
      # Upstream serve_engine defaults (temperature=1.0, top_p=0.95,
      # top_k=50). Greedy (temperature=0) collapses the audio codebook
      # argmax to a fixed value after a few steps; sampling with diversity
      # is required for natural-sounding speech.
      temperature: 1.0
      top_p: 0.95
      top_k: 50
      # Cap Stage-0 to 1024 audio frames (~40 s at 25 fps). The audio-eos
      # natural stop (128012, forced by the talker's _apply_audio_mode_bias
      # at ramp-completion) typically fires earlier and trims this.
      max_tokens: 1024
      seed: 42
      repetition_penalty: 1.0

  - stage_id: 1
    max_num_seqs: 4
    gpu_memory_utilization: 0.25
    enforce_eager: true
    trust_remote_code: true
    enable_prefix_caching: false
    async_scheduling: false
    # Prefill length is num_codebooks * num_frames; 8 * 8192 = 65536 covers
    # the upper bound at the per-request 250-frame Stage-0 cap above plus
    # headroom for batching multiple requests.
    max_num_batched_tokens: 65536
    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