diff --git a/timm/models/layers/weight_init.py b/timm/models/layers/weight_init.py
index 4a160931..943e4f4c 100644
--- a/timm/models/layers/weight_init.py
+++ b/timm/models/layers/weight_init.py
@@ -5,7 +5,7 @@ import warnings
 from torch.nn.init import _calculate_fan_in_and_fan_out
 
 
-def _no_grad_trunc_normal_(tensor, mean, std, a, b):
+def _trunc_normal_(tensor, mean, std, a, b):
     # Cut & paste from PyTorch official master until it's in a few official releases - RW
     # Method based on https://people.sc.fsu.edu/~jburkardt/presentations/truncated_normal.pdf
     def norm_cdf(x):
@@ -17,28 +17,27 @@ def _no_grad_trunc_normal_(tensor, mean, std, a, b):
                       "The distribution of values may be incorrect.",
                       stacklevel=2)
 
-    with torch.no_grad():
-        # Values are generated by using a truncated uniform distribution and
-        # then using the inverse CDF for the normal distribution.
-        # Get upper and lower cdf values
-        l = norm_cdf((a - mean) / std)
-        u = norm_cdf((b - mean) / std)
+    # Values are generated by using a truncated uniform distribution and
+    # then using the inverse CDF for the normal distribution.
+    # Get upper and lower cdf values
+    l = norm_cdf((a - mean) / std)
+    u = norm_cdf((b - mean) / std)
 
-        # Uniformly fill tensor with values from [l, u], then translate to
-        # [2l-1, 2u-1].
-        tensor.uniform_(2 * l - 1, 2 * u - 1)
+    # Uniformly fill tensor with values from [l, u], then translate to
+    # [2l-1, 2u-1].
+    tensor.uniform_(2 * l - 1, 2 * u - 1)
 
-        # Use inverse cdf transform for normal distribution to get truncated
-        # standard normal
-        tensor.erfinv_()
+    # Use inverse cdf transform for normal distribution to get truncated
+    # standard normal
+    tensor.erfinv_()
 
-        # Transform to proper mean, std
-        tensor.mul_(std * math.sqrt(2.))
-        tensor.add_(mean)
+    # Transform to proper mean, std
+    tensor.mul_(std * math.sqrt(2.))
+    tensor.add_(mean)
 
-        # Clamp to ensure it's in the proper range
-        tensor.clamp_(min=a, max=b)
-        return tensor
+    # Clamp to ensure it's in the proper range
+    tensor.clamp_(min=a, max=b)
+    return tensor
 
 
 def trunc_normal_(tensor, mean=0., std=1., a=-2., b=2.):
@@ -64,7 +63,8 @@ def trunc_normal_(tensor, mean=0., std=1., a=-2., b=2.):
         >>> w = torch.empty(3, 5)
         >>> nn.init.trunc_normal_(w)
     """
-    return _no_grad_trunc_normal_(tensor, mean, std, a, b)
+    with torch.no_grad():
+        return _trunc_normal_(tensor, mean, std, a, b)
 
 
 def trunc_normal_tf_(tensor, mean=0., std=1., a=-2., b=2.):
@@ -90,8 +90,8 @@ def trunc_normal_tf_(tensor, mean=0., std=1., a=-2., b=2.):
         >>> w = torch.empty(3, 5)
         >>> nn.init.trunc_normal_(w)
     """
-    _no_grad_trunc_normal_(tensor, 0, 1.0, a, b)
     with torch.no_grad():
+        _trunc_normal_(tensor, 0, 1.0, a, b)
         tensor.mul_(std).add_(mean)
     return tensor
 
@@ -111,10 +111,12 @@ def variance_scaling_(tensor, scale=1.0, mode='fan_in', distribution='normal'):
         # constant is stddev of standard normal truncated to (-2, 2)
         trunc_normal_tf_(tensor, std=math.sqrt(variance) / .87962566103423978)
     elif distribution == "normal":
-        tensor.normal_(std=math.sqrt(variance))
+        with torch.no_grad():
+            tensor.normal_(std=math.sqrt(variance))
     elif distribution == "uniform":
         bound = math.sqrt(3 * variance)
-        tensor.uniform_(-bound, bound)
+        with torch.no_grad():
+            tensor.uniform_(-bound, bound)
     else:
         raise ValueError(f"invalid distribution {distribution}")