Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-28 15:18:26 +01:00
Code Issues Packages Projects Releases Wiki Activity

server-parallel : add "--reverse-prompt" + compiler warning fixes

Browse Source
This commit is contained in:
Georgi Gerganov 2023-10-06 14:32:19 +03:00
parent afc09db51c
commit 5ab6c2132a
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 26 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
examples/server-parallel/server.cpp
View File

@ -1,13 +1,15 @@
#include <chrono>
#include "frontend.h"
#include "common.h"
#include "llama.h"
#include "../server/httplib.h"
#include "../server/json.hpp"
#include <iostream>
#include <sstream>
#include <thread>
#include <vector>
#include "frontend.h"
#include "common.h"
#include "llama.h"
#include <chrono>
using namespace httplib;
using namespace std;
@ -241,9 +243,7 @@ struct server_parallel_context {
string prompt = data.value("prompt", "");
for (llama_client_slot & slot : slots)
{
if (
slot_id == -1 && slot.available() ||
slot.id == slot_id)
if ((slot_id == -1 && slot.available()) || slot.id == slot_id)
{
slot.start(prompt, temperature);
LOG_TEE("slot %i is processing\n", slot.id);
@ -429,8 +429,6 @@ struct server_parallel_context {
slot.generated_text += token_str;
slot.sampled = id;
size_t pos = 0;
size_t stop_pos =
findStoppingStrings(slot.generated_text, token_str.size(), STOP_FULL);
@ -740,20 +738,34 @@ static void server_params_parse(int argc, char **argv, server_params &sparams,
else if (arg == "--numa")
{
params.numa = true;
} else if (arg == "-cb" || arg == "--cont-batching") {
} else if (arg == "-cb" || arg == "--cont-batching")
{
params.cont_batching = true;
} else if (arg == "-np" || arg == "--parallel") {
if (++i >= argc) {
}
else if (arg == "-np" || arg == "--parallel")
{
if (++i >= argc)
{
invalid_param = true;
break;
}
params.n_parallel = std::stoi(argv[i]);
} else if (arg == "-n" || arg == "--n-predict") {
if (++i >= argc) {
} else if (arg == "-n" || arg == "--n-predict")
{
if (++i >= argc)
{
invalid_param = true;
break;
}
params.n_predict = std::stoi(argv[i]);
} else if (arg == "-r" || arg == "--reverse-prompt")
{
if (++i >= argc)
{
invalid_param = true;
break;
}
params.antiprompt.push_back(argv[i]);
}
else
{