recipe.yaml

quant_stage:
  quant_modifiers:
    QuantizationModifier:
      ignore: [lm_head]
      config_groups:
        group_0:
          weights: {num_bits: 8, type: float, strategy: channel, dynamic: false, symmetric: true}
          input_activations: {num_bits: 8, type: float, strategy: token, dynamic: true, symmetric: true}
          targets: [Linear]
      kv_cache_scheme: {num_bits: 8, type: float, strategy: tensor, dynamic: false, symmetric: true}