diff --git a/unsloth/kernels/cross_entropy_loss.py b/unsloth/kernels/cross_entropy_loss.py
index fbb14013ff..cdd5b1cf12 100644
--- a/unsloth/kernels/cross_entropy_loss.py
+++ b/unsloth/kernels/cross_entropy_loss.py
@@ -301,6 +301,7 @@ class Fast_CrossEntropyLoss(torch.autograd.Function):
         vocab_size: int
         n_rows, vocab_size = logits.shape
         device = logits.device
+        labels = labels.to(device)
 
         div, mod = divmod(vocab_size, MAX_FUSED_SIZE)
         n_chunks: int = div + (mod != 0)