| quant_stage: | |
| quant_modifiers: | |
| QuantizationModifier: | |
| ignore: [lm_head] | |
| config_groups: | |
| fp8_linear: | |
| 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] | |
| fp8_attention: | |
| output_activations: {num_bits: 8, type: float, strategy: channel, dynamic: false, | |
| symmetric: true} | |
| targets: ['re:.*q_proj.weight', 're:.*k_proj.weight', 're:.*v_proj.weight'] | |