recipe.yaml

default_stage:
  default_modifiers:
    QuantizationModifier:
      targets: [Linear]
      ignore: ['re:.*lm_head', 're:.*self_attn', 're:.*router', 're:.*vision_model.*', 're:.*multi_modal_projector.*',
        Llama4TextAttention]
      scheme: FP8_BLOCK