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

remove redundant code

Browse source
This commit is contained in:
Xuan Son Nguyen 2024-10-24 16:23:55 +02:00
parent c34ab08a16
commit 575b1332ab
1 changed files with 1 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

10
examples/server/server.cpp
View file

@ -715,10 +715,6 @@ struct server_context {
metrics.init(); metrics.init();
} }
std::vector<llama_token> tokenize(const json & json_prompt, bool add_special, bool parse_special) const {
return tokenize_mixed(ctx, json_prompt, add_special, parse_special);
}
server_slot * get_slot_by_id(int id) { server_slot * get_slot_by_id(int id) {
for (server_slot & slot : slots) { for (server_slot & slot : slots) {
if (slot.id == id) { if (slot.id == id) {
@ -1352,10 +1348,6 @@ struct server_context {
std::vector<server_task> create_tasks_cmpl(json data, server_task_cmpl_type cmpl_type) { std::vector<server_task> create_tasks_cmpl(json data, server_task_cmpl_type cmpl_type) {
std::vector<server_task> tasks; std::vector<server_task> tasks;
auto create_task = [&](json & task_data, llama_tokens & prompt_tokens) { auto create_task = [&](json & task_data, llama_tokens & prompt_tokens) {
if (prompt_tokens.empty()) {
// TODO @ngxson : should not throw an error
throw std::runtime_error("prompt must not be empty");
}
SRV_DBG("create task, n_tokens = %d\n", (int) prompt_tokens.size()); SRV_DBG("create task, n_tokens = %d\n", (int) prompt_tokens.size());
server_task task; server_task task;
task.id = queue_tasks.get_new_id(); task.id = queue_tasks.get_new_id();
@ -2877,7 +2869,7 @@ int main(int argc, char ** argv) {
const bool add_special = json_value(body, "add_special", false); const bool add_special = json_value(body, "add_special", false);
const bool with_pieces = json_value(body, "with_pieces", false); const bool with_pieces = json_value(body, "with_pieces", false);
std::vector<llama_token> tokens = ctx_server.tokenize(body.at("content"), add_special, true); std::vector<llama_token> tokens = tokenize_mixed(ctx_server.ctx, body.at("content"), add_special, true);
if (with_pieces) { if (with_pieces) {
for (const auto& token : tokens) { for (const auto& token : tokens) {