diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index 637b40337..c25338f57 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -754,7 +754,7 @@ struct server_context {
         default_generation_settings_for_props = get_formated_generation(slots.front());
         default_generation_settings_for_props["seed"] = -1;
 
-        // the update_slots() logic will always submit a maximum of n_batch or n_parralel tokens
+        // 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)
         {
             const int32_t n_batch = llama_n_batch(ctx);