LLM inference in C/C++
C++ ggml
common : avoid side effects around params parsing (#29537)
Georgi Gerganova97cce86a8ad
diff --git a/common/arg.cpp b/common/arg.cppindex 63e342776d..2acac3b5cf 100644--- a/common/arg.cpp+++ b/common/arg.cpp@@ -2673,16 +2673,17 @@ common_params_context common_params_parser_init(common_params & params, llama_exparams.video_ffmpeg_bin_dir = value;}).set_examples(mmproj_examples).set_env("LLAMA_ARG_VIDEO_FFMPEG_DIR"));- if (params.is_gen_docs || llama_supports_rpc()) {- add_opt(common_arg(- {"--rpc"}, "SERVERS",- "comma-separated list of RPC servers (host:port)",- [](common_params & params, const std::string & value) {- add_rpc_devices(value);- GGML_UNUSED(params);+ add_opt(common_arg(+ {"--rpc"}, "SERVERS",+ "comma-separated list of RPC servers (host:port)",+ [](common_params & params, const std::string & value) {+ if (!llama_supports_rpc()) {+ throw std::invalid_argument("RPC not supported in this build");}- ).set_env("LLAMA_ARG_RPC"));- }+ add_rpc_devices(value);+ GGML_UNUSED(params);+ }+ ).set_env("LLAMA_ARG_RPC"));add_opt(common_arg({"-lm", "--load-mode"}, "MODE","model loading mode (default: auto)\n"diff --git a/tools/server/server.cpp b/tools/server/server.cppindex 049bdcebb3..4568a11fb9 100644--- a/tools/server/server.cpp+++ b/tools/server/server.cpp@@ -102,12 +102,12 @@ int llama_server(int argc, char ** argv) {// touch it. lifecycle is symmetric, stop_gc() runs in clean_up() before backend freeserver_stream_session_manager_start();- SRV_INF("%s", "initializing ...\n");-if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_SERVER)) {return 1;}+ SRV_INF("%s", "initializing ...\n");+llama_backend_init();llama_numa_init(params.numa);