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

Add --simple-io option for subprocesses and break out console.h and cpp (#1558)

Browse source
This commit is contained in:
DannyDaemonic 2023-08-04 08:20:12 -07:00 • committed by GitHub
parent 5f631c2679
commit 3498588e0f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
7 changed files with 536 additions and 435 deletions
Download patch file Download diff file Expand all files Collapse all files

29
examples/main/main.cpp
View file

@ -4,6 +4,7 @@
#endif
#include "common.h"
#include "console.h"
#include "llama.h"
#include "build-info.h"
#include "grammar-parser.h"
@ -35,9 +36,7 @@
#pragma warning(disable: 4244 4267) // possible loss of data
#endif
static console_state con_st;
static llama_context ** g_ctx;
static bool is_interacting = false;
#if defined (__unix__) || (defined (__APPLE__) && defined (__MACH__)) || defined (_WIN32)
@ -46,7 +45,7 @@ void sigint_handler(int signo) {
if (!is_interacting) {
is_interacting=true;
} else {
console_cleanup(con_st);
console::cleanup();
printf("\n");
llama_print_timings(*g_ctx);
_exit(130);
@ -64,10 +63,8 @@ int main(int argc, char ** argv) {
// save choice to use color for later
// (note for later: this is a slightly awkward choice)
con_st.use_color = params.use_color;
con_st.multiline_input = params.multiline_input;
console_init(con_st);
atexit([]() { console_cleanup(con_st); });
console::init(params.simple_io, params.use_color);
atexit([]() { console::cleanup(); });
if (params.perplexity) {
printf("\n************\n");
@ -373,7 +370,7 @@ int main(int argc, char ** argv) {
if (params.interactive) {
const char *control_message;
if (con_st.multiline_input) {
if (params.multiline_input) {
control_message = " - To return control to LLaMa, end your input with '\\'.\n"
" - To return control without starting a new line, end your input with '/'.\n";
} else {
@ -401,7 +398,7 @@ int main(int argc, char ** argv) {
int n_past_guidance = 0;
// the first thing we will do is to output the prompt, so set color accordingly
console_set_color(con_st, CONSOLE_COLOR_PROMPT);
console::set_display(console::prompt);
std::vector<llama_token> embd;
std::vector<llama_token> embd_guidance;
@ -422,9 +419,9 @@ int main(int argc, char ** argv) {
// Ensure the input doesn't exceed the context size by truncating embd if necessary.
if ((int)embd.size() > max_embd_size) {
auto skipped_tokens = embd.size() - max_embd_size;
console_set_color(con_st, CONSOLE_COLOR_ERROR);
console::set_display(console::error);
printf("<<input too long: skipped %zu token%s>>", skipped_tokens, skipped_tokens != 1 ? "s" : "");
console_set_color(con_st, CONSOLE_COLOR_DEFAULT);
console::set_display(console::reset);
fflush(stdout);
embd.resize(max_embd_size);
}
@ -667,7 +664,7 @@ int main(int argc, char ** argv) {
}
// reset color to default if we there is no pending user input
if (input_echo && (int)embd_inp.size() == n_consumed) {
console_set_color(con_st, CONSOLE_COLOR_DEFAULT);
console::set_display(console::reset);
}
// if not currently processing queued inputs;
@ -693,7 +690,7 @@ int main(int argc, char ** argv) {
if (last_output.find(antiprompt.c_str(), search_start_pos) != std::string::npos) {
if (params.interactive) {
is_interacting = true;
console_set_color(con_st, CONSOLE_COLOR_USER_INPUT);
console::set_display(console::user_input);
}
is_antiprompt = true;
fflush(stdout);
@ -714,7 +711,7 @@ int main(int argc, char ** argv) {
is_interacting = true;
printf("\n");
console_set_color(con_st, CONSOLE_COLOR_USER_INPUT);
console::set_display(console::user_input);
fflush(stdout);
} else if (params.instruct) {
is_interacting = true;
@ -739,12 +736,12 @@ int main(int argc, char ** argv) {
std::string line;
bool another_line = true;
do {
another_line = console_readline(con_st, line);
another_line = console::readline(line, params.multiline_input);
buffer += line;
} while (another_line);
// done taking input, reset color
console_set_color(con_st, CONSOLE_COLOR_DEFAULT);
console::set_display(console::reset);
// Add tokens to embd only if the input buffer is non-empty
// Entering a empty line lets the user pass control back