PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
[HPU]Fix compile bug when quant layer (#441)
Yi Liu19601d4ed977
diff --git a/auto_round/autoround.py b/auto_round/autoround.pyindex 5c0f0c66e..7cadb49fa 100644--- a/auto_round/autoround.py+++ b/auto_round/autoround.py@@ -495,7 +495,7 @@ class AutoRound(object):device = next(self.model.parameters()).deviceif self.enable_torch_compile != False:try:- quant_layer = compile_func(self.quant_layer, device, self.enable_torch_compile)+ quant_layer = compile_func(self.quant_layer, self.device, self.enable_torch_compile)except:logger.warning("torch compile failed, reset it to `False`")self.enable_torch_compile = False