# Single-Hopper streaming throughput profile: AR32 / codec32, Flow10.
# Automatically selected on Hopper devices with at least 140 GiB (H200)
# when nvidia-cuda-mps-control is available on PATH.
# Standard sampling is configured below; request stream=true for first audio.
# F0 and HiFT stay FP32; only deterministic HiFT decode is graphed.
# HiFT graphs capture on the third use of each exact shape, adding latency then.
# The codec graph pool is not capped by gpu_memory_utilization; leave memory headroom.
base_config: cosyvoice3_packed_streaming.yaml
stages:
  - stage_id: 0
    max_num_seqs: 32
    hf_overrides:
      cosyvoice3_sampling_mode: standard
    default_sampling_params:
      max_tokens: 2048
      repetition_penalty: 1.21
      temperature: 0.7
      top_k: 20
      top_p: 0.8
  - stage_id: 1
    max_num_seqs: 32
    env:
      COSYVOICE3_TRT: "0"
      COSYVOICE3_BATCH_FLOW: "1"
      COSYVOICE3_FULL_RESPONSE_OPTIMIZATIONS: "0"
      COSYVOICE3_PACKED_STREAMING: "1"
      COSYVOICE3_CACHED_ISTFT: "1"
      COSYVOICE3_HIFT_GRAPH: "1"