diff --git a/common/common.cpp b/common/common.cpp index 3203faddd634a..c2c79433dd8e6 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -995,6 +995,14 @@ std::vector gpt_params_parser_init(gpt_params & params, llama_example params.flash_attn = true; } ).set_env("LLAMA_ARG_FLASH_ATTN")); + add_opt(llama_arg( + {"--no-perf"}, + format("disable internal libllama performance timings (default: %s)", params.no_perf ? "true" : "false"), + [](gpt_params & params) { + params.no_perf = true; + params.sparams.no_perf = true; + } + ).set_env("LLAMA_ARG_FLASH_ATTN")); add_opt(llama_arg( {"-p", "--prompt"}, "PROMPT", ex == LLAMA_EXAMPLE_MAIN