remove performence output

d5a0fda9 · zhuwenwen · fed04a1c · d5a0fda9
Commit d5a0fda9 authored Nov 01, 2023 by zhuwenwen
Hide whitespace changes
Inline Side-by-side

Showing with 3 additions and 3 deletions

examples/cpp/llama/llama_example.cc examples/cpp/llama/llama_example.cc +3 -3

No files found.
--- a/examples/cpp/llama/llama_example.cc
+++ b/examples/cpp/llama/llama_example.cc
@@ -505,9 +505,9 @@ void llama_example(const INIReader reader)
           vocab_size,
           ((end.tv_sec - start.tv_sec) * 1000 + (end.tv_usec - start.tv_usec) * 0.001) / ite);
-    float total_time;
+    // float total_time;
-    total_time = ((end.tv_sec - start.tv_sec) * 1000 + (end.tv_usec - start.tv_usec) * 0.001) / ite / 1000;
+    // total_time = ((end.tv_sec - start.tv_sec) * 1000 + (end.tv_usec - start.tv_usec) * 0.001) / ite / 1000;
-    printf("[INFO] performance: %.2f tokens/sec \n", (request_batch_size * request_output_len) / total_time);
+    // printf("[INFO] performance: %.2f tokens/sec \n", (request_batch_size * request_output_len) / total_time);
    ftNcclParamDestroy(tensor_para);
    ftNcclParamDestroy(pipeline_para);