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

llama : remove mtest (#3177)

Browse source 
* Remove mtest

* remove from common/common.h and examples/main/main.cpp
This commit is contained in:
Roland 2023-09-15 03:28:45 -04:00 • committed by GitHub
parent 98311c4277
commit 2d770505a8
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 3 additions and 26 deletions
Download patch file Download diff file Expand all files Collapse all files

4
common/common.cpp
View file

@ -434,8 +434,6 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
#endif // GGML_USE_CUBLAS
} else if (arg == "--no-mmap") {
params.use_mmap = false;
} else if (arg == "--mtest") {
params.mem_test = true;
} else if (arg == "--numa") {
params.numa = true;
} else if (arg == "--export") {
@ -687,7 +685,6 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
printf(" Not recommended since this is both slower and uses more VRAM.\n");
#endif // GGML_USE_CUBLAS
#endif
printf(" --mtest compute maximum memory usage\n");
printf(" --export export the computation graph to 'llama.ggml'\n");
printf(" --verbose-prompt print prompt before generation\n");
fprintf(stderr, " --simple-io use basic IO for better compatibility in subprocesses and limited consoles\n");
@ -1225,7 +1222,6 @@ void dump_non_result_info_yaml(FILE * stream, const gpt_params & params, const l
fprintf(stream, "mlock: %s # default: false\n", params.use_mlock ? "true" : "false");
fprintf(stream, "model: %s # default: models/7B/ggml-model.bin\n", params.model.c_str());
fprintf(stream, "model_draft: %s # default:\n", params.model_draft.c_str());
fprintf(stream, "mtest: %s # default: false\n", params.mem_test ? "true" : "false");
fprintf(stream, "multiline_input: %s # default: false\n", params.multiline_input ? "true" : "false");
fprintf(stream, "n_gpu_layers: %d # default: -1\n", params.n_gpu_layers);
fprintf(stream, "n_predict: %d # default: -1 (unlimited)\n", params.n_predict);

1
common/common.h
View file

@ -110,7 +110,6 @@ struct gpt_params {
bool perplexity = false; // compute perplexity over the prompt
bool use_mmap = true; // use mmap for faster loads
bool use_mlock = false; // use mlock to keep model in memory
bool mem_test = false; // compute maximum memory usage
bool numa = false; // attempt optimizations that help on some NUMA systems
bool export_cgraph = false; // export the computation graph
bool verbose_prompt = false; // print prompt tokens before generation