diff options
Diffstat (limited to 'examples/common.cpp')
| -rw-r--r-- | examples/common.cpp | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/examples/common.cpp b/examples/common.cpp index 6ac48455..00230273 100644 --- a/examples/common.cpp +++ b/examples/common.cpp @@ -343,6 +343,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) { params.use_mmap = false; } else if (arg == "--mtest") { params.mem_test = true; + } else if (arg == "--numa") { + params.numa = true; } else if (arg == "--export") { params.export_cgraph = true; } else if (arg == "--verbose-prompt") { @@ -488,6 +490,9 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) { if (llama_mmap_supported()) { fprintf(stderr, " --no-mmap do not memory-map model (slower load but may reduce pageouts if not using mlock)\n"); } + fprintf(stderr, " --numa attempt optimizations that help on some NUMA systems\n"); + fprintf(stderr, " if run without this previously, it is recommended to drop the system page cache before using this\n"); + fprintf(stderr, " see https://github.com/ggerganov/llama.cpp/issues/1437\n"); #ifdef LLAMA_SUPPORTS_GPU_OFFLOAD fprintf(stderr, " -ngl N, --n-gpu-layers N\n"); fprintf(stderr, " number of layers to store in VRAM\n"); |