vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

rpc : disable options for non-RPC builds

Browse source
This commit is contained in:
Radoslav Gerganov 2024-09-03 16:46:35 +03:00
parent 0178724414
commit 7049733bcc
2 changed files with 8 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

4
common/common.cpp
View file

@ -1234,11 +1234,13 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa
#endif // GGML_USE_CUDA_SYCL_VULKAN
return true;
}
#ifdef GGML_USE_RPC
if (arg == "--rpc") {
CHECK_ARG
params.rpc_servers = argv[i];
return true;
}
#endif
if (arg == "--no-mmap") {
params.use_mmap = false;
return true;
@ -1929,7 +1931,9 @@ void gpt_params_print_usage(int /*argc*/, char ** argv, const gpt_params & param
options.push_back({ "*", " --image FILE", "path to an image file. use with multimodal models. Specify multiple times for batching" });
options.push_back({ "backend" });
#ifdef GGML_USE_RPC
options.push_back({ "*", " --rpc SERVERS", "comma separated list of RPC servers" });
#endif
if (llama_supports_mlock()) {
options.push_back({ "*", " --mlock", "force system to keep model in RAM rather than swapping or compressing" });

4
examples/llama-bench/llama-bench.cpp
View file

@ -299,7 +299,9 @@ static void print_usage(int /* argc */, char ** argv) {
printf(" --cpu-strict <0|1> (default: %s)\n", join(cmd_params_defaults.cpu_strict, ",").c_str());
printf(" --poll <0...100> (default: %s)\n", join(cmd_params_defaults.poll, ",").c_str());
printf(" -ngl, --n-gpu-layers <n> (default: %s)\n", join(cmd_params_defaults.n_gpu_layers, ",").c_str());
#ifdef GGML_USE_RPC
printf(" -rpc, --rpc <rpc_servers> (default: %s)\n", join(cmd_params_defaults.rpc_servers, ",").c_str());
#endif
printf(" -sm, --split-mode <none|layer|row> (default: %s)\n", join(transform_to_str(cmd_params_defaults.split_mode, split_mode_str), ",").c_str());
printf(" -mg, --main-gpu <i> (default: %s)\n", join(cmd_params_defaults.main_gpu, ",").c_str());
printf(" -nkvo, --no-kv-offload <0|1> (default: %s)\n", join(cmd_params_defaults.no_kv_offload, ",").c_str());
@ -482,12 +484,14 @@ static cmd_params parse_cmd_params(int argc, char ** argv) {
}
auto p = string_split<int>(argv[i], split_delim);
params.n_gpu_layers.insert(params.n_gpu_layers.end(), p.begin(), p.end());
#ifdef GGML_USE_RPC
} else if (arg == "-rpc" || arg == "--rpc") {
if (++i >= argc) {
invalid_param = true;
break;
}
params.rpc_servers.push_back(argv[i]);
#endif
} else if (arg == "-sm" || arg == "--split-mode") {
if (++i >= argc) {
invalid_param = true;