quant_stage:
  quant_modifiers:
    QuantizationModifier:
      config_groups:
        fp8_block_lm_head:
          targets: ['re:.*lm_head']
          weights:
            num_bits: 8
            type: float
            symmetric: true
            group_size: null
            strategy: block
            block_structure: [128, 128]
            dynamic: false
            actorder: null
            scale_dtype: null
            zp_dtype: null
            observer: memoryless_minmax
            observer_kwargs: {}
          input_activations:
            num_bits: 8
            type: float
            symmetric: true
            group_size: 128
            strategy: group
            block_structure: null
            dynamic: true
            actorder: null
            scale_dtype: null
            zp_dtype: null
            observer: null
            observer_kwargs: {}
          output_activations: null
          format: null
        nvfp4_linear:
          targets: [Linear]
          weights:
            num_bits: 4
            type: float
            symmetric: true
            group_size: 16
            strategy: tensor_group
            block_structure: null
            dynamic: false
            actorder: null
            scale_dtype: null
            zp_dtype: null
            observer: memoryless_minmax
            observer_kwargs: {}
          input_activations:
            num_bits: 4
            type: float
            symmetric: true
            group_size: 16
            strategy: tensor_group
            block_structure: null
            dynamic: local
            actorder: null
            scale_dtype: null
            zp_dtype: null
            observer: minmax
            observer_kwargs: {}
          output_activations: null
          format: null
      targets: [Linear]
      ignore: ['re:visual.*', 're:model.visual.*', 're:.*mlp.gate$', 're:.*embed_tokens$',
        're:.*shared_expert_gate$', 're:.*linear_attn.*']
      bypass_divisibility_checks: false