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

Add --n-probs to server CLI args

Browse source
This commit is contained in:
Samuel Stevens 2023-09-19 13:03:41 -04:00
parent 8781013ef6
commit bd1553a4b7
1 changed files with 11 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

11
examples/server/server.cpp
View file

@ -737,6 +737,7 @@ static void server_print_usage(const char *argv0, const gpt_params &params,
printf(" --path PUBLIC_PATH path from which to serve static files (default %s)\n", sparams.public_path.c_str()); printf(" --path PUBLIC_PATH path from which to serve static files (default %s)\n", sparams.public_path.c_str());
printf(" -to N, --timeout N server read/write timeout in seconds (default: %d)\n", sparams.read_timeout); printf(" -to N, --timeout N server read/write timeout in seconds (default: %d)\n", sparams.read_timeout);
printf(" --embedding enable embedding vector output (default: %s)\n", params.embedding ? "enabled" : "disabled"); printf(" --embedding enable embedding vector output (default: %s)\n", params.embedding ? "enabled" : "disabled");
printf(" --n-probs number of token probabilities to output (default: %d)\n", params.n_probs);
printf("\n"); printf("\n");
} }
@ -861,6 +862,16 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
params.n_batch = std::stoi(argv[i]); params.n_batch = std::stoi(argv[i]);
params.n_batch = std::min(512, params.n_batch); params.n_batch = std::min(512, params.n_batch);
} }
else if (arg == "--n-probs")
{
if (++i >= argc)
{
invalid_param = true;
break;
}
params.n_probs = std::stoi(argv[i]);
params.n_probs = std::min(0, params.n_probs);
}
else if (arg == "--gpu-layers" || arg == "-ngl" || arg == "--n-gpu-layers") else if (arg == "--gpu-layers" || arg == "-ngl" || arg == "--n-gpu-layers")
{ {
if (++i >= argc) if (++i >= argc)