fix server

Author: ngxson

examples/server/server.cpp

@@ -1959,7 +1959,7 @@ struct server_context {
 
         // the update_slots() logic will always submit a maximum of n_batch or n_parallel tokens
         // note that n_batch can be > n_ctx (e.g. for non-causal attention models such as BERT where the KV cache is not used)
-        batch.clear();
+        batch = llama_batch_ext_ptr(ctx);
         metrics.init();
     }