switch XPU ccl backend to torch-builtin xccl in test_zero3_integration

src/accelerate/test_utils/scripts/external_deps/test_zero3_integration.py

@@ -28,7 +28,7 @@
 @require_huggingface_suite
 def init_torch_dist_then_launch_deepspeed():
     if torch_device == "xpu":
-        backend = "ccl"
+        backend = "xccl"
     elif torch_device == "hpu":
         backend = "hccl"
     else:

src/accelerate/test_utils/scripts/test_script.py

@@ -48,11 +48,7 @@
 )
 
 
-# TODO: remove RegressionModel4XPU once ccl support empty buffer in broadcasting.
-if is_xpu_available():
-    from accelerate.test_utils import RegressionModel4XPU as RegressionModel
-else:
-    from accelerate.test_utils import RegressionModel
+from accelerate.test_utils import RegressionModel
 
 if is_hpu_available():
     ATOL = 1e-3

src/accelerate/test_utils/training.py

@@ -1,4 +1,5 @@
 # Copyright 2021 The HuggingFace Team. All rights reserved.
+# Copyright 2021 The HuggingFace Team. All rights reserved.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -33,20 +34,6 @@ def __getitem__(self, i):
         return {"x": self.x[i], "y": self.y[i]}
 
 
-class RegressionModel4XPU(torch.nn.Module):
-    def __init__(self, a=0, b=0, double_output=False):
-        super().__init__()
-        self.a = torch.nn.Parameter(torch.tensor([2, 3]).float())
-        self.b = torch.nn.Parameter(torch.tensor([2, 3]).float())
-        self.first_batch = True
-
-    def forward(self, x=None):
-        if self.first_batch:
-            print(f"Model dtype: {self.a.dtype}, {self.b.dtype}. Input dtype: {x.dtype}")
-            self.first_batch = False
-        return x * self.a[0] + self.b[0]
-
-
 class RegressionModel(torch.nn.Module):
     def __init__(self, a=0, b=0, double_output=False):
         super().__init__()