Revert "Support using mmap when applying LoRA (#2095)" (#2206)

Has perf regression when mlock is used.

This reverts commit 2347463201a9f4159ae95b737e1544dd300569c8.

1 files changed, 2 insertions, 1 deletions

diff --git a/examples/common.cpp b/examples/common.cpp
index fd551c9c..94875b05 100644
--- a/examples/common.cpp
+++ b/examples/common.cpp
@@ -285,6 +285,7 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
                 break;
             }
             params.lora_adapter = argv[i];
+            params.use_mmap = false;
         } else if (arg == "--lora-base") {
             if (++i >= argc) {
                 invalid_param = true;
@@ -520,7 +521,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     fprintf(stderr, "  --mtest               compute maximum memory usage\n");
     fprintf(stderr, "  --export              export the computation graph to 'llama.ggml'\n");
     fprintf(stderr, "  --verbose-prompt      print prompt before generation\n");
-    fprintf(stderr, "  --lora FNAME          apply LoRA adapter\n");
+    fprintf(stderr, "  --lora FNAME          apply LoRA adapter (implies --no-mmap)\n");
     fprintf(stderr, "  --lora-base FNAME     optional model to use as a base for the layers modified by the LoRA adapter\n");
     fprintf(stderr, "  -m FNAME, --model FNAME\n");
     fprintf(stderr, "                        model path (default: %s)\n", params.model.c_str());