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

--memory_f32 flag to --memory-f32 to match common.cpp

Browse source
This commit is contained in:
digiwombat 2023-05-28 13:58:25 -04:00
parent 655899db89
commit b38d41ef52
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/server/server.cpp
View file

@ -298,7 +298,7 @@ void server_print_usage(int /*argc*/, char **argv, const gpt_params &params, con
fprintf(stderr, "options:\n"); fprintf(stderr, "options:\n");
fprintf(stderr, " -h, --help show this help message and exit\n"); fprintf(stderr, " -h, --help show this help message and exit\n");
fprintf(stderr, " -t N, --threads N number of threads to use during computation (default: %d)\n", params.n_threads); fprintf(stderr, " -t N, --threads N number of threads to use during computation (default: %d)\n", params.n_threads);
fprintf(stderr, " --memory_f32 use f32 instead of f16 for memory key+value\n"); fprintf(stderr, " --memory-f32 use f32 instead of f16 for memory key+value\n");
fprintf(stderr, " -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch); fprintf(stderr, " -b N, --batch-size N batch size for prompt processing (default: %d)\n", params.n_batch);
fprintf(stderr, " --embedding enable embedding mode\n"); fprintf(stderr, " --embedding enable embedding mode\n");
fprintf(stderr, " --keep number of tokens to keep from the initial prompt (default: %d, -1 = all)\n", params.n_keep); fprintf(stderr, " --keep number of tokens to keep from the initial prompt (default: %d, -1 = all)\n", params.n_keep);
@ -386,7 +386,7 @@ bool server_params_parse(int argc, char **argv, server_params &sparams, gpt_para
} }
params.n_ctx = std::stoi(argv[i]); params.n_ctx = std::stoi(argv[i]);
} }
else if (arg == "--memory_f32") else if (arg == "--memory-f32")
{ {
params.memory_f16 = false; params.memory_f16 = false;
} }