default_stage:
  default_modifiers:
    QuantizationModifier:
      config_groups:
        group_fp8:
          targets: [Linear]
          weights:
            num_bits: 8
            type: float
            symmetric: true
            group_size: null
            strategy: channel
            block_structure: null
            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: null
            strategy: token
            block_structure: null
            dynamic: true
            actorder: null
            scale_dtype: null
            zp_dtype: null
            observer: null
            observer_kwargs: {}
          output_activations: null
          format: null
      targets: [Linear]
      ignore: [lm_head, 're:model\.embed_tokens$', 're:visual.*', 're:model\.visual.*', 're:.*\.self_attn\.o_proj$',
        're:.*\.linear_attn\.out_proj$', 're:.*\.mlp\.gate$', 're:.*\.mlp\.shared_expert_gate$',
        're:.*\.linear_attn\.in_proj_b$', 're:.*\.linear_attn\.in_proj_a$']
      bypass_divisibility_checks: false