PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
move packeding res to cpu (#1104)
Yi Liudaa151d495c3
diff --git a/auto_round/compressors/base.py b/auto_round/compressors/base.pyindex a3309bc41..8bf788c24 100644--- a/auto_round/compressors/base.py+++ b/auto_round/compressors/base.py@@ -1332,6 +1332,8 @@ class BaseCompressor(object):self._immediate_pack(name)if to_cpu:m = m.to("cpu")+ packed_m = get_module(self.model, name)+ set_module(self.model, name, packed_m.to("cpu"))else:if to_cpu:m = m.to("cpu")