# HunyuanImage-3.0-Instruct AR-only deploy.
#
# Use this when AR and DiT are deployed as independent services. This file
# resolves to stage 0 only, avoiding the default two-stage topology.
pipeline: hunyuan_image3_ar
async_chunk: false

stages:
  - stage_id: 0
    max_num_seqs: 1
    gpu_memory_utilization: 0.75
    trust_remote_code: true
    enforce_eager: true
    enable_prefix_caching: false
    max_num_batched_tokens: 32768
    devices: "0,1,2,3"
    tensor_parallel_size: 4
    hf_overrides:
      rope_parameters:
        mrope_section: [0, 32, 32]
        rope_type: default
    default_sampling_params:
      temperature: 0.0
      top_p: 0.95
      top_k: 1024
      max_tokens: 1024
      detokenize: true

platforms:
  npu:
    stages:
      - stage_id: 0
        gpu_memory_utilization: 0.75
        devices: "0,1,2,3,4,5,6,7"
        tensor_parallel_size: 8
        max_num_batched_tokens: 8192

  xpu:
    stages:
      - stage_id: 0
        gpu_memory_utilization: 0.95
        devices: "0,1,2,3,4,5,6,7"
        tensor_parallel_size: 8
        max_num_batched_tokens: 32784
        quantization: fp8
        enable_expert_parallel: true
        worker_cls: vllm_omni.platforms.xpu.worker.xpu_ar_worker.XPUARWorker