context : remove redundant explicit casting to the same type (ggml-org#15948)

The function 'output_reserve' return type is 'uint32_t', so need to add
explicit casting.

Author: haiyuewa

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");
             }