# AuK deploy: thinker encoder (stage 0) + rectified-flow DiT (stage 1).
# Topology declared in vllm_omni/model_executor/models/auk/pipeline.py.
#
# Fields omitted from a stage fall back to StageDeployConfig dataclass
# defaults (see vllm_omni/config/stage_config.py). trust_remote_code,
# enable_prefix_caching and enable_chunked_prefill are pipeline-wide
# DeployConfig fields and apply to both stages.
#
# The ODE runs over the whole target segment, so there is nothing to stream
# between the stages: async_chunk stays off.
async_chunk: false
trust_remote_code: true
# Prefix caching must stay off: a cache hit skips the prefix positions, and
# the fused [tokens, 2048] condition needs every position of the prompt.
# Chunked prefill works (the runner concatenates the per-chunk hidden states)
# but measured no wall-time gain, since the encoder is a few percent of a
# request, and it costs bit-exact reproducibility across scheduling.
enable_prefix_caching: false
enable_chunked_prefill: false

stages:
  # Stage 0: Qwen2.5-Omni thinker as a frozen text encoder.
  # Prefill only — one sampled token, discarded downstream. eager because the
  # fused-hidden forward walks the decoder layers itself and so bypasses the
  # compiled graph.
  - stage_id: 0
    devices: "0"
    max_num_seqs: 1
    gpu_memory_utilization: 0.45
    enforce_eager: true
    max_num_batched_tokens: 32768
    # AuK takes text plus at most one clip; no image or video tower is built.
    limit_mm_per_prompt: {audio: 1}
    default_sampling_params:
      temperature: 0.0
      max_tokens: 1
      detokenize: false
      seed: 0

  # Stage 1: AuKPipeline (DiT + BigVGAN-flow VAE encoder and decoder).
  # Shares GPU 0 with the encoder; 32 Euler steps at CFG 2.0 is the Base
  # recipe, and AuK-Flash overrides both with its distilled 4-step grid.
  - stage_id: 1
    devices: "0"
    max_num_seqs: 1
    gpu_memory_utilization: 0.35
    enforce_eager: true
    default_sampling_params:
      seed: 0
      num_inference_steps: 32
      guidance_scale: 2.0