diff --git a/comfy/quant_ops.py b/comfy/quant_ops.py
index d2f3e7397..9b924560b 100644
--- a/comfy/quant_ops.py
+++ b/comfy/quant_ops.py
@@ -425,7 +425,8 @@ class TensorCoreFP8Layout(QuantizedLayout):
     @staticmethod
     def dequantize(qdata, scale, orig_dtype, **kwargs):
         plain_tensor = torch.ops.aten._to_copy.default(qdata, dtype=orig_dtype)
-        return plain_tensor * scale
+        plain_tensor.mul_(scale)
+        return plain_tensor
 
     @classmethod
     def get_plain_tensors(cls, qtensor):
diff --git a/requirements.txt b/requirements.txt
index 9291552d3..e0b2c566b 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,5 +1,5 @@
 comfyui-frontend-package==1.32.9
-comfyui-workflow-templates==0.7.20
+comfyui-workflow-templates==0.7.23
 comfyui-embedded-docs==0.3.1
 torch
 torchsde