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

fix /slots endpoint

Browse source
This commit is contained in:
Xuan Son Nguyen 2024-12-07 16:35:13 +01:00
parent 1881ffaf3e
commit 01da1ed9b6
2 changed files with 3 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

1
examples/server/server.cpp
View file

@ -2233,6 +2233,7 @@ struct server_context {
auto res = std::make_unique<server_task_result_metrics>();
res->id = task.id;
res->slots_data = slots_data;
res->n_idle_slots = n_idle_slots;
res->n_processing_slots = n_processing_slots;
res->n_tasks_deferred = queue_tasks.queue_tasks_deferred.size();

4
examples/server/utils.hpp
View file

@ -327,12 +327,12 @@ static std::string llama_get_chat_template(const struct llama_model * model) {
std::string template_key = "tokenizer.chat_template";
// call with NULL buffer to get the total size of the string
int32_t res = llama_model_meta_val_str(model, template_key.c_str(), NULL, 0);
if (res < 0) {
if (res < 2) {
return "";
} else {
std::vector<char> model_template(res, 0);
llama_model_meta_val_str(model, template_key.c_str(), model_template.data(), model_template.size());
return std::string(model_template.data(), model_template.size());
return std::string(model_template.data(), model_template.size() - 1);
}
}