# MiniCPM-o 4.5 deploy: 2-GPU layout (thinker on GPU 0, talker on GPU 1).
#
# Stage 0 (thinker): GPU 0 — multimodal understanding, ~90% mem (thinker
#                            gets a dedicated card, so it can take more of
#                            the GPU than the single-GPU co-located layout).
# Stage 1 (talker) : GPU 1 — MiniCPMTTS + Token2Wav, ~75% mem
#                            (covers both the talker LM and the in-process
#                            Token2Wav vocoder that emits the waveform).
#
# Use this when you have two GPUs and want the talker + Token2Wav vocoder
# on its own card instead of sharing GPU 0 with the thinker (the default
# single-GPU layout co-locates both and can OOM under load).
pipeline: minicpmo_4_5
async_chunk: false

trust_remote_code: true
enable_prefix_caching: false

stages:
  - stage_id: 0
    max_num_seqs: 16
    gpu_memory_utilization: 0.9
    enforce_eager: false
    tensor_parallel_size: 1
    max_num_batched_tokens: 16384
    devices: "0"
    limit_mm_per_prompt:
      video: 1
    default_sampling_params:
      temperature: 0.0
      top_p: 1.0
      top_k: -1
      max_tokens: 2048
      seed: 42
      detokenize: true
      repetition_penalty: 1.1

  - stage_id: 1
    # Talker only consumes runtime_additional_information[0]; any value > 1
    # makes concurrent requests share request-0's audio (mm_outputs fallback).
    max_num_seqs: 1
    gpu_memory_utilization: 0.75
    enforce_eager: false
    max_num_batched_tokens: 8192
    devices: "1"
    default_sampling_params:
      temperature: 0.0
      top_p: 1.0
      top_k: -1
      max_tokens: 1
      seed: 42
      detokenize: false

platforms:
  npu:
    stages:
      - stage_id: 0
        max_num_batched_tokens: 8192
        compilation_config:
          cudagraph_mode: PIECEWISE
      - stage_id: 1
        max_num_batched_tokens: 8192
        compilation_config:
          cudagraph_mode: PIECEWISE