Update eagle/model/modeling_minicpm_kv.py

eagle/model/modeling_minicpm_kv.py

@@ -934,7 +934,7 @@ class MiniCPMFlashAttention2(MiniCPMAttention):
             value_states = value_states.to(target_dtype)
 
         attn_output = self._flash_attention_forward(
-            query_states, key_states, value_states, attention_mask, q_len, dropout=dropout_rate
+            query_states, key_states, value_states, None, q_len, dropout=dropout_rate
         )
 
         attn_output = attn_output.reshape(bsz, q_len, self.hidden_size).contiguous()