PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
awq exporting bugfix (#456)
WeiweiZhang15ccdb0d119d7
diff --git a/auto_round/export/export_to_awq/export.py b/auto_round/export/export_to_awq/export.pyindex 7f3a8d33f..0a6146bea 100644--- a/auto_round/export/export_to_awq/export.py+++ b/auto_round/export/export_to_awq/export.py@@ -50,7 +50,7 @@ def pack_layer(name, model, layer_config, backend, pbar):scale, zp = linear_layer.scale, linear_layer.zpscale = scale.t().contiguous()zp = zp.t().contiguous()- config["zp"] = config["zp"].to(torch.float32)+ # config["zp"] = config["zp"].to(torch.float32)bits = config["bits"]group_size = config["group_size"]