diff --git a/src/llama-context.cpp b/src/llama-context.cpp
index 3e163001c180b..289a32b6d3473 100644
--- a/src/llama-context.cpp
+++ b/src/llama-context.cpp
@@ -181,7 +181,7 @@ llama_context::llama_context(
         // graph outputs buffer
         {
             // resized during inference when a batch uses more outputs
-            if ((uint32_t) output_reserve(params.n_seq_max) < params.n_seq_max) {
+            if (output_reserve(params.n_seq_max) < params.n_seq_max) {
                 throw std::runtime_error("failed to reserve initial output buffer");
             }