root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 02:44:36 +00:00
Code Issues Actions 9 Packages Projects Releases Wiki Activity

main : allow empty --prompt-cache file (#5176)

Browse Source 
* allow empty --prompt-cache file

This allows the use of std::tmpnam(), std::tmpfile(), Python's tempfile.NamedTemporaryFile(), and similar create-empty-file API's for the user.

I switched from the C fopen API to the C++ filesystem api to get around the fact that, to the best of my knowledge, C has no portable way to get the file size above LONG_MAX, with std::ftell() returning long? fallback to std::ifstream for c++  < 17
(the project is currently targeting C++11 it seems - file_exists() and file_size() can be removed when we upgrade to c++17)

* formatting

(requested in codereview)

* remove c++17, file_is_empty
This commit is contained in:
divinity76 2024-01-30 10:18:02 +01:00 committed by GitHub
parent 5589921ef8
commit 813416991a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
examples/main/main.cpp
View File

@ -39,6 +39,17 @@ static std::ostringstream * g_output_ss;
static std::vector<llama_token> * g_output_tokens; static std::vector<llama_token> * g_output_tokens;
static bool is_interacting = false; static bool is_interacting = false;
static bool file_exists(const std::string &path) {
std::ifstream f(path.c_str());
return f.good();
}
static bool file_is_empty(const std::string &path) {
std::ifstream f;
f.exceptions(std::ifstream::failbit | std::ifstream::badbit);
f.open(path.c_str(), std::ios::in | std::ios::binary | std::ios::ate);
return f.tellg() == 0;
}
static void write_logfile( static void write_logfile(
const llama_context * ctx, const gpt_params & params, const llama_model * model, const llama_context * ctx, const gpt_params & params, const llama_model * model,
@ -215,12 +226,12 @@ int main(int argc, char ** argv) {
if (!path_session.empty()) { if (!path_session.empty()) {
LOG_TEE("%s: attempting to load saved session from '%s'\n", __func__, path_session.c_str()); LOG_TEE("%s: attempting to load saved session from '%s'\n", __func__, path_session.c_str());
if (!file_exists(path_session)) {
// fopen to check for existing session LOG_TEE("%s: session file does not exist, will create.\n", __func__);
FILE * fp = std::fopen(path_session.c_str(), "rb"); } else if (file_is_empty(path_session)) {
if (fp != NULL) { LOG_TEE("%s: The session file is empty. A new session will be initialized.\n", __func__);
std::fclose(fp); } else {
// The file exists and is not empty
session_tokens.resize(n_ctx); session_tokens.resize(n_ctx);
size_t n_token_count_out = 0; size_t n_token_count_out = 0;
if (!llama_load_session_file(ctx, path_session.c_str(), session_tokens.data(), session_tokens.capacity(), &n_token_count_out)) { if (!llama_load_session_file(ctx, path_session.c_str(), session_tokens.data(), session_tokens.capacity(), &n_token_count_out)) {
@ -229,10 +240,7 @@ int main(int argc, char ** argv) {
} }
session_tokens.resize(n_token_count_out); session_tokens.resize(n_token_count_out);
llama_set_rng_seed(ctx, params.seed); llama_set_rng_seed(ctx, params.seed);
LOG_TEE("%s: loaded a session with prompt size of %d tokens\n", __func__, (int)session_tokens.size());
LOG_TEE("%s: loaded a session with prompt size of %d tokens\n", __func__, (int) session_tokens.size());
} else {
LOG_TEE("%s: session file does not exist, will create\n", __func__);
} }
} }