From 2d770505a89a99ce78a5950cf14fc06d3176ffa4 Mon Sep 17 00:00:00 2001
From: Roland <14355895+rbur0425@users.noreply.github.com>
Date: Fri, 15 Sep 2023 03:28:45 -0400
Subject: llama : remove mtest (#3177)

* Remove mtest

* remove from common/common.h and examples/main/main.cpp
---
 common/common.cpp | 4 ----
 common/common.h   | 1 -
 2 files changed, 5 deletions(-)

(limited to 'common')

diff --git a/common/common.cpp b/common/common.cpp
index afc9b8a5..9969cb97 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -434,8 +434,6 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
 #endif // GGML_USE_CUBLAS
         } else if (arg == "--no-mmap") {
             params.use_mmap = false;
-        } else if (arg == "--mtest") {
-            params.mem_test = true;
         } else if (arg == "--numa") {
             params.numa = true;
         } else if (arg == "--export") {
@@ -687,7 +685,6 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     printf("                        Not recommended since this is both slower and uses more VRAM.\n");
 #endif // GGML_USE_CUBLAS
 #endif
-    printf("  --mtest               compute maximum memory usage\n");
     printf("  --export              export the computation graph to 'llama.ggml'\n");
     printf("  --verbose-prompt      print prompt before generation\n");
     fprintf(stderr, "  --simple-io           use basic IO for better compatibility in subprocesses and limited consoles\n");
@@ -1225,7 +1222,6 @@ void dump_non_result_info_yaml(FILE * stream, const gpt_params & params, const l
     fprintf(stream, "mlock: %s # default: false\n", params.use_mlock ? "true" : "false");
     fprintf(stream, "model: %s # default: models/7B/ggml-model.bin\n", params.model.c_str());
     fprintf(stream, "model_draft: %s # default:\n", params.model_draft.c_str());
-    fprintf(stream, "mtest: %s # default: false\n", params.mem_test ? "true" : "false");
     fprintf(stream, "multiline_input: %s # default: false\n", params.multiline_input ? "true" : "false");
     fprintf(stream, "n_gpu_layers: %d # default: -1\n", params.n_gpu_layers);
     fprintf(stream, "n_predict: %d # default: -1 (unlimited)\n", params.n_predict);
diff --git a/common/common.h b/common/common.h
index 238635ae..4979f99d 100644
--- a/common/common.h
+++ b/common/common.h
@@ -110,7 +110,6 @@ struct gpt_params {
     bool perplexity        = false; // compute perplexity over the prompt
     bool use_mmap          = true;  // use mmap for faster loads
     bool use_mlock         = false; // use mlock to keep model in memory
-    bool mem_test          = false; // compute maximum memory usage
     bool numa              = false; // attempt optimizations that help on some NUMA systems
     bool export_cgraph     = false; // export the computation graph
     bool verbose_prompt    = false; // print prompt tokens before generation
-- 
cgit v1.2.3