# 量化配置

apiversion: multimodal_sd_modelslim_v1

metadata:

  config_id: wan2_2_w8a8_mxfp8_i2v

  score: 0.95

  verified_model_types:

    - Wan2_2

    - Wan2.2

  label:

    w_bit: 8

    a_bit: 8

    is_sparse: False

    kv_cache: False



spec:

  process:

    - type: "linear_quant"

      qconfig:

        act:

          scope: "per_block"   # default is per_tensor

          dtype: "mxfp8"        # default is int8

          symmetric: True      # default is True

          method: "minmax"      # default is minmax

        weight:

          scope: "per_block"   # default is per_channel

          dtype: "mxfp8"        # default is int8

          symmetric: True       # default is True

          method: "minmax"      # default is minmax

      include:

        - "*"



  save:

    - type: "mindie_format_saver"

      part_file_size: 0



  # 基础配置

  multimodal_sd_config:

    dump_config:

      capture_mode: "args"

      dump_data_dir: ""  # default is save_path

    model_config:

      prompt: "A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots, and carries a black purse. She wears sunglasses and red lipstick. She walks confidently and casually. The street is damp and reflective, creating a mirror effect of the colorful lights. Many pedestrians walk about."

      # 模型加载参数

      convert_model_dtype: True

      task: "i2v-A14B"