PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
hot fix for nfp4 scheme (#784)
Wenhua Cheng7e52af2a17fc
diff --git a/auto_round/schemes.py b/auto_round/schemes.pyindex e556acd29..496af179c 100644--- a/auto_round/schemes.py+++ b/auto_round/schemes.py@@ -120,7 +120,7 @@ NVFP4 = QuantizationScheme.from_dict("group_size": 16,"data_type": "nv_fp","act_bits": 4,- "act_data_type": "nv_fp_with_static_gs",+ "act_data_type": "nv_fp4_with_static_gs",})