diff --git a/ultralytics/__init__.py b/ultralytics/__init__.py
index 0de65e61..4cf03a48 100644
--- a/ultralytics/__init__.py
+++ b/ultralytics/__init__.py
@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.3.55"
+__version__ = "8.3.56"
 
 import os
 
diff --git a/ultralytics/engine/exporter.py b/ultralytics/engine/exporter.py
index 5a249caf..eb5c7807 100644
--- a/ultralytics/engine/exporter.py
+++ b/ultralytics/engine/exporter.py
@@ -603,7 +603,7 @@ class Exporter:
     @try_export
     def export_paddle(self, prefix=colorstr("PaddlePaddle:")):
         """YOLO Paddle export."""
-        check_requirements(("paddlepaddle", "x2paddle"))
+        check_requirements(("paddlepaddle-gpu" if torch.cuda.is_available() else "paddlepaddle", "x2paddle"))
         import x2paddle  # noqa
         from x2paddle.convert import pytorch2paddle  # noqa
 
diff --git a/ultralytics/nn/autobackend.py b/ultralytics/nn/autobackend.py
index 9edfa11d..70962e8e 100644
--- a/ultralytics/nn/autobackend.py
+++ b/ultralytics/nn/autobackend.py
@@ -133,7 +133,7 @@ class AutoBackend(nn.Module):
 
         # Set device
         cuda = torch.cuda.is_available() and device.type != "cpu"  # use CUDA
-        if cuda and not any([nn_module, pt, jit, engine, onnx]):  # GPU dataloader formats
+        if cuda and not any([nn_module, pt, jit, engine, onnx, paddle]):  # GPU dataloader formats
             device = torch.device("cpu")
             cuda = False