default_stage: default_modifiers: QuantizationModifier: targets: [Linear] ignore: [lm_head, 're:.*embed_tokens.*', 're:.*\.visual\..*', 're:.*visual\..*', 're:.*linear_attn\..*', 're:.*norm.*', 're:.*q_norm.*', 're:.*k_norm.*'] scheme: NVFP4 bypass_divisibility_checks: false