Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 13:28:50 +01:00
Code Issues Packages Projects Releases Wiki Activity

Adding support for the --numa argument for llama-bench. (#7080)

Browse Source
This commit is contained in:
kunnis 2024-05-05 07:17:47 -05:00 committed by GitHub
parent 8f8acc8683
commit 628b299106
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
examples/llama-bench/llama-bench.cpp
View File

@ -178,6 +178,7 @@ struct cmd_params {
std::vector<std::vector<float>> tensor_split; std::vector<std::vector<float>> tensor_split;
std::vector<bool> use_mmap; std::vector<bool> use_mmap;
std::vector<bool> embeddings; std::vector<bool> embeddings;
ggml_numa_strategy numa;
int reps; int reps;
bool verbose; bool verbose;
output_formats output_format; output_formats output_format;
@ -200,6 +201,7 @@ static const cmd_params cmd_params_defaults = {
/* tensor_split */ {std::vector<float>(llama_max_devices(), 0.0f)}, /* tensor_split */ {std::vector<float>(llama_max_devices(), 0.0f)},
/* use_mmap */ {true}, /* use_mmap */ {true},
/* embeddings */ {false}, /* embeddings */ {false},
/* numa */ GGML_NUMA_STRATEGY_DISABLED,
/* reps */ 5, /* reps */ 5,
/* verbose */ false, /* verbose */ false,
/* output_format */ MARKDOWN /* output_format */ MARKDOWN
@ -224,6 +226,7 @@ static void print_usage(int /* argc */, char ** argv) {
printf(" -nkvo, --no-kv-offload <0|1> (default: %s)\n", join(cmd_params_defaults.no_kv_offload, ",").c_str()); printf(" -nkvo, --no-kv-offload <0|1> (default: %s)\n", join(cmd_params_defaults.no_kv_offload, ",").c_str());
printf(" -fa, --flash-attn <0|1> (default: %s)\n", join(cmd_params_defaults.flash_attn, ",").c_str()); printf(" -fa, --flash-attn <0|1> (default: %s)\n", join(cmd_params_defaults.flash_attn, ",").c_str());
printf(" -mmp, --mmap <0|1> (default: %s)\n", join(cmd_params_defaults.use_mmap, ",").c_str()); printf(" -mmp, --mmap <0|1> (default: %s)\n", join(cmd_params_defaults.use_mmap, ",").c_str());
printf(" --numa <distribute|isolate|numactl> (default: disabled)\n");
printf(" -embd, --embeddings <0|1> (default: %s)\n", join(cmd_params_defaults.embeddings, ",").c_str()); printf(" -embd, --embeddings <0|1> (default: %s)\n", join(cmd_params_defaults.embeddings, ",").c_str());
printf(" -ts, --tensor-split <ts0/ts1/..> (default: 0)\n"); printf(" -ts, --tensor-split <ts0/ts1/..> (default: 0)\n");
printf(" -r, --repetitions <n> (default: %d)\n", cmd_params_defaults.reps); printf(" -r, --repetitions <n> (default: %d)\n", cmd_params_defaults.reps);
@ -396,6 +399,17 @@ static cmd_params parse_cmd_params(int argc, char ** argv) {
} }
auto p = split<bool>(argv[i], split_delim); auto p = split<bool>(argv[i], split_delim);
params.no_kv_offload.insert(params.no_kv_offload.end(), p.begin(), p.end()); params.no_kv_offload.insert(params.no_kv_offload.end(), p.begin(), p.end());
} else if (arg == "--numa") {
if (++i >= argc) {
invalid_param = true;
break;
} else {
std::string value(argv[i]);
/**/ if (value == "distribute" || value == "" ) { params.numa = GGML_NUMA_STRATEGY_DISTRIBUTE; }
else if (value == "isolate") { params.numa = GGML_NUMA_STRATEGY_ISOLATE; }
else if (value == "numactl") { params.numa = GGML_NUMA_STRATEGY_NUMACTL; }
else { invalid_param = true; break; }
}
} else if (arg == "-fa" || arg == "--flash-attn") { } else if (arg == "-fa" || arg == "--flash-attn") {
if (++i >= argc) { if (++i >= argc) {
invalid_param = true; invalid_param = true;
@ -1215,6 +1229,7 @@ int main(int argc, char ** argv) {
llama_log_set(llama_null_log_callback, NULL); llama_log_set(llama_null_log_callback, NULL);
} }
llama_backend_init(); llama_backend_init();
llama_numa_init(params.numa);
// initialize printer // initialize printer
std::unique_ptr<printer> p; std::unique_ptr<printer> p;