# Ming-flash-omni-2.0 thinker-only deploy: multimodal understanding -> text.
#
# Single-stage configuration that drops the talker; useful when only text
# output is required (chat / understanding / reasoning)
#
# Stage 0: Thinker — TP=4 across GPUs 0-3 with full memory budget since no
# talker shares the last device.
pipeline: ming_flash_omni_thinker_only
async_chunk: false

trust_remote_code: true
distributed_executor_backend: mp
enable_prefix_caching: false

stages:
  - stage_id: 0
    max_num_seqs: 1
    gpu_memory_utilization: 0.9
    enforce_eager: false
    tensor_parallel_size: 4
    max_num_batched_tokens: 32768
    devices: "0,1,2,3"
    # disable fused allreduce+rms for flashinfer version mismatch for now
    compilation_config:
      pass_config:
        fuse_allreduce_rms: false
    default_sampling_params:
      temperature: 0.4
      top_p: 0.9
      max_tokens: 2048
      repetition_penalty: 1.05
      detokenize: true
      ignore_eos: false

# Ming-flash-omni-2.0 has only been verified on CUDA devices
platforms: {}