recipe.yaml

test_stage:
  quant_modifiers:
    vLLMQuantizationModifier:
      ignore: [lm_head, model.layers.0.mlp.down_proj]
      config_groups:
        group_0:
          weights: {num_bits: 8, type: int, symmetric: true, strategy: tensor}
          input_activations: {num_bits: 8, type: int, symmetric: true, strategy: token, dynamic: true}
          output_activations: null
          targets: [Linear]
    SparseGPTModifier:
      sparsity: 0.0
      block_size: 128
      sequential_update: false
      quantize: true
      targets: ['re:model.layers.\d+$']