PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
fix gguf opt-rtn regression (#1905)
Wenhua Chengdc5e67f343d5
diff --git a/auto_round/export/export_to_gguf/convert.py b/auto_round/export/export_to_gguf/convert.pyindex 539c90c00..61ac14bb5 100644--- a/auto_round/export/export_to_gguf/convert.py+++ b/auto_round/export/export_to_gguf/convert.py@@ -237,12 +237,12 @@ def _quant_data(cls, data_torch, data_qtype, name, modify_name, new_name, bid, dlayer_name = namemodule = get_module(cls.model, layer_name)kwargs = {- "scale": None,- "zp": None,- "d_scale": None,- "d_wmin": None,- "wmin": None,- "imatrix": None,+ "scale": module.scale if hasattr(module, "scale") else None,+ "zp": module.zp if hasattr(module, "zp") else None,+ "d_scale": module.w_d_scale if hasattr(module, "w_d_scale") else None,+ "d_wmin": module.w_d_wmin if hasattr(module, "w_d_wmin") else None,+ "wmin": module.w_wmin if hasattr(module, "w_wmin") else None,+ "imatrix": module.imatrix if hasattr(module, "imatrix") else None,}# patch for Qwen3_5, Qwen3_5 handles some weights specially,# but the scale doesn't match; these weights are handled by gguf itself.