Add batch warmup to sweep-bench (#375)

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

common/common.cpp

@@ -1468,6 +1468,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
         params.warmup = false;
         return true;
     }
+    if (arg == "--warmup-batch" || arg == "-wb") {
+        params.batch_warmup = true;
+        return true;
+    }
     if (arg == "--output-format") {
         CHECK_ARG
         std::string value(argv[i]);

common/common.h

@@ -200,6 +200,7 @@ struct gpt_params {
     bool dump_kv_cache     = false; // dump the KV cache contents for debugging purposes
     bool no_kv_offload     = false; // disable KV offloading
     bool warmup            = true;  // warmup run
+    bool batch_warmup      = false; // batch warmup run
     bool check_tensors     = false; // validate tensor data
     bool repack_tensors    = false; // repack tensors if interleaved variant is available
     bool use_thp           = false; // use transparent huge pages (linux only)