File size: 209 Bytes
5ca509a |
1 2 3 4 5 6 7 |
default_stage:
default_modifiers:
QuantizationModifier:
targets: [Linear]
ignore: ['re:.*lm_head', 're:.*self_attn', 're:.*attn', 're:.*attention.*', 're:.*router']
scheme: FP8_DYNAMIC
|