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

Interim commit

Browse source
This commit is contained in:
pudepiedj 2023-10-03 09:46:53 +01:00
parent d673691619
commit 51196a44dc
2 changed files with 15 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

2
common/common.h
View file

@ -79,7 +79,7 @@ struct gpt_params {
std::string model_draft = ""; // draft model for speculative decoding
std::string model_alias = "unknown"; // model alias
std::string prompt = "";
std::string prompt_file = ""; // store for external prompt file name
std::string prompt_file = ""; // store the external prompt file name
std::string path_prompt_cache = ""; // path to file for saving/loading prompt eval state
std::string input_prefix = ""; // string to prefix user inputs with
std::string input_suffix = ""; // string to suffix user inputs with

24
examples/parallel/parallel.cpp
View file

@ -72,13 +72,17 @@ struct client {
std::vector<llama_token> tokens_prev;
};
static void printDateTime() {
std::time_t currentTime = std::time(nullptr);
std::cout << "\n\033[35mRUN PARAMETERS as at \033[0m" << std::ctime(&currentTime);
static void print_date_time() {
std::time_t current_time = std::time(nullptr);
std::tm* local_time = std::localtime(&current_time);
char buffer[80];
strftime(buffer, sizeof(buffer), "%Y-%m-%d %H:%M:%S", local_time);
printf("\n\033[35mrun parameters as at %s\033[0m\n", buffer);
}
// Define a split string function to ...
static std::vector<std::string> splitString(const std::string& input, char delimiter) {
static std::vector<std::string> split_string(const std::string& input, char delimiter) {
std::vector<std::string> tokens;
std::istringstream stream(input);
std::string token;
@ -124,18 +128,18 @@ int main(int argc, char ** argv) {
// load the prompts from an external file if there are any
if (params.prompt.empty()) {
std::cout << "\n\033[32mNo new questions so proceed with build-in defaults.\033[0m";
printf("\n\033[32mNo new questions so proceed with build-in defaults.\033[0m");
} else {
// Output each line of the input params.prompts vector and copy to k_prompts
int index = 0;
std::cout << "\n\033[32mNow printing the external prompt file " << params.prompt_file << "\033[0m\n\n";
printf("\n\033[32mNow printing the external prompt file %s\033[0m\n\n", params.prompt_file);
std::vector<std::string> prompts = splitString(params.prompt, '\n');
std::vector<std::string> prompts = split_string(params.prompt, '\n');
for (const auto& prompt : prompts) {
k_prompts.resize(index + 1);
k_prompts[index] = prompt;
index++;
std::cout << std::setw(2) << std::right << index << " prompt: " << prompt << std::endl;
printf("%3d prompt: %s\n", index, prompt);
}
}
@ -392,10 +396,10 @@ int main(int argc, char ** argv) {
const auto t_main_end = ggml_time_us();
printDateTime();
print_date_time();
LOG_TEE("\n%s: n_parallel = %d, n_sequences = %d, cont_batching = %d, system tokens = %d\n", __func__, n_clients, n_seq, cont_batching, n_tokens_system);
std::cout << "external prompt file (if any): " << params.prompt_file << "\n\n";
printf("external prompt file (if any): %s \n\n", params.prompt_file);
LOG_TEE("Total prompt tokens: %6d, speed: %5.2f t/s\n", n_total_prompt, (double) (n_total_prompt ) / (t_main_end - t_main_start) * 1e6);
LOG_TEE("Total gen tokens: %6d, speed: %5.2f t/s\n", n_total_gen, (double) (n_total_gen ) / (t_main_end - t_main_start) * 1e6);