add n_threads_batch to system info, refactor to get_system_info()

common/common.cpp

@@ -611,7 +611,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     printf("  -s SEED, --seed SEED  RNG seed (default: -1, use random seed for < 0)\n");
     printf("  -t N, --threads N     number of threads to use during generation (default: %d)\n", params.n_threads);
     printf("  -tb N, --threads-batch N\n");
-    printf("                        number of threads to use during batch evaluation and prompt processing (default: same as --threads)\n");
+    printf("                        number of threads to use during batch and prompt processing (default: same as --threads)\n");
     printf("  -p PROMPT, --prompt PROMPT\n");
     printf("                        prompt to start generation with (default: empty)\n");
     printf("  -e, --escape          process prompt escapes sequences (\\n, \\r, \\t, \\', \\\", \\\\)\n");
@@ -703,6 +703,19 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     printf("\n");
 }
 
+std::string get_system_info(const gpt_params & params) {
+    std::ostringstream os;
+
+    os << "system_info: n_threads = " << params.n_threads;
+    if (params.n_threads_batch != -1) {
+        os << " (n_threads_batch = " << params.n_threads_batch << ")";
+    }
+    os << " / " << std::thread::hardware_concurrency() << " | " << llama_print_system_info();
+
+    return os.str();
+}
+
+
 std::string gpt_random_prompt(std::mt19937 & rng) {
     const int r = rng() % 10;
     switch (r) {

common/common.h

@@ -124,6 +124,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params);
 
 void gpt_print_usage(int argc, char ** argv, const gpt_params & params);
 
+std::string get_system_info(const gpt_params & params);
+
 std::string gpt_random_prompt(std::mt19937 & rng);
 
 //

examples/embd-input/embd-input-lib.cpp

@@ -48,8 +48,7 @@ struct MyModel* create_mymodel(int argc, char ** argv) {
     // print system information
     {
         fprintf(stderr, "\n");
-        fprintf(stderr, "system_info: n_threads = %d / %d | %s\n",
+        fprintf(stderr, "%s\n", get_system_info(params).c_str());
-                params.n_threads, std::thread::hardware_concurrency(), llama_print_system_info());
     }
     struct MyModel * ret = new MyModel();
     ret->ctx = ctx;

examples/embedding/embedding.cpp

@@ -53,8 +53,7 @@ int main(int argc, char ** argv) {
     // print system information
     {
         fprintf(stderr, "\n");
-        fprintf(stderr, "system_info: n_threads = %d / %d | %s\n",
+        fprintf(stderr, "%s\n", get_system_info(params).c_str());
-                params.n_threads, std::thread::hardware_concurrency(), llama_print_system_info());
     }
 
     int n_past = 0;

examples/main/main.cpp

@@ -201,8 +201,7 @@ int main(int argc, char ** argv) {
     // print system information
     {
         LOG_TEE("\n");
-        LOG_TEE("system_info: n_threads = %d / %d | %s\n",
+        LOG_TEE("%s\n", get_system_info(params).c_str());
-                params.n_threads, std::thread::hardware_concurrency(), llama_print_system_info());
     }
 
     // export the cgraph and exit

examples/perplexity/perplexity.cpp

@@ -708,8 +708,7 @@ int main(int argc, char ** argv) {
     // print system information
     {
         fprintf(stderr, "\n");
-        fprintf(stderr, "system_info: n_threads = %d / %d | %s\n",
+        fprintf(stderr, "%s\n", get_system_info(params).c_str());
-                params.n_threads, std::thread::hardware_concurrency(), llama_print_system_info());
     }
 
     struct results_perplexity results;

examples/server/server.cpp

@@ -1286,6 +1286,7 @@ int main(int argc, char **argv)
                             {"commit", BUILD_COMMIT}});
     LOG_INFO("system info", {
                                 {"n_threads", params.n_threads},
+                                {"n_threads_batch", params.n_threads_batch},
                                 {"total_threads", std::thread::hardware_concurrency()},
                                 {"system_info", llama_print_system_info()},
                             });