diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py
index 25ad680008..60fa43bc8e 100644
--- a/unsloth/models/llama.py
+++ b/unsloth/models/llama.py
@@ -266,7 +266,7 @@ def LlamaAttention_fast_forward_inference(
         self.paged_attention_K = self.paged_attention[:,0]
         self.paged_attention_V = self.paged_attention[:,1]
         self.paged_attention_K[:seq_len] = K1.permute(2, 0, 1, 3)
-        self.paged_attention_K[:seq_len] = K1.permute(2, 0, 1, 3)
+        self.paged_attention_K[:seq_len] = V1.permute(2, 0, 1, 3)
     pass
     self.paged_attention_K[seq_len] = Kn.permute(2, 0, 1, 3)
     self.paged_attention_V[seq_len] = Vn.permute(2, 0, 1, 3)