Skip to content

PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度

fix ipex tqdm mismatch issue (#293)

wenhuach21487abd6f9f9f
diff --git a/README.md b/README.md
index c622ba4b7..ca6abfa34 100644
--- a/README.md
+++ b/README.md
@@ -54,7 +54,7 @@ pip install auto-round
## Model Quantization
-### Basic Usage ((Gaudi2/CPU/GPU))
+### Basic Usage (Gaudi2/CPU/GPU)
A user guide detailing the full list of supported arguments is provided by calling ```auto-round -h``` on the terminal.
Alternatively, you can use ```auto_round``` instead of ```auto-round```.
diff --git a/auto_round/auto_quantizer.py b/auto_round/auto_quantizer.py
index 859481302..0cfbf0729 100644
--- a/auto_round/auto_quantizer.py
+++ b/auto_round/auto_quantizer.py
@@ -582,9 +582,12 @@ class AutoRoundQuantizer(HfQuantizer):
def cpu_post_init(self, model):
dep_check = True
message = "Repacking to CPU format"
+ layers = [] ## ipex post_init will add one more layer
+ for n,m in model.named_modules():
+ layers.append((n,m))
- for n, layer in tqdm(model.named_modules(), desc=message, total=len(list(model.named_modules())),
- leave=True): ##not exit correctly
+ for n, layer in tqdm(layers, desc=message, total=len(layers),
+ leave=True):
if isinstance(layer, (qlinear_qbits.QuantLinear, qlinear_qbits_gptq.QuantLinear)):
if dep_check:
layer.req_check()