# VoxCPM2 deploy: single-stage AR pipeline with per-request state batching.
# Verified on 1x H20 141GB.
#
# Fields omitted from a stage fall back to StageDeployConfig defaults (see
# vllm_omni/config/stage_config.py). Notable choices:
#   * enforce_eager=true because the talker's KV-cache save/restore loop is
#     not cudagraph-compatible (captured separately via voxcpm2_talker's own
#     _CapturedGraph path).
#   * max_num_seqs=4 matches the legacy max_batch_size=4 contract: concurrent
#     requests are supported via per-request StaticKVCache save/restore.
async_chunk: false
dtype: bfloat16

stages:
  - stage_id: 0
    max_num_seqs: 4
    gpu_memory_utilization: 0.9
    enforce_eager: true
    trust_remote_code: true
    enable_prefix_caching: false
    async_scheduling: true
    max_num_batched_tokens: 4096
    max_model_len: 4096
    devices: "0"
    default_sampling_params:
      temperature: 0.0
      top_p: 1.0
      top_k: -1
      max_tokens: 4096
      seed: 42
      repetition_penalty: 1.0