Skip to content
This repository was archived by the owner on Jul 4, 2025. It is now read-only.

feat: add warmup model back #146

Merged
merged 1 commit into from
Nov 16, 2023
Merged

feat: add warmup model back #146

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 15 additions & 13 deletions controllers/llamaCPP.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,18 +96,19 @@ std::string create_return_json(const std::string &id, const std::string &model,
}

void llamaCPP::warmupModel() {
// json pseudo;
//
// pseudo["prompt"] = "Hello";
// pseudo["n_predict"] = 10;
// const int task_id = llama.request_completion(pseudo, false);
// std::string completion_text;
// task_result result = llama.next_result(task_id);
// if (!result.error && result.stop) {
// LOG_INFO << result.result_json.dump(-1, ' ', false,
// json::error_handler_t::replace);
// }
// return;
json pseudo;

pseudo["prompt"] = "Hello";
pseudo["n_predict"] = 10;
pseudo["stream"] = false;
const int task_id = llama.request_completion(pseudo, false, false);
std::string completion_text;
task_result result = llama.next_result(task_id);
if (!result.error && result.stop) {
LOG_INFO << result.result_json.dump(-1, ' ', false,
json::error_handler_t::replace);
}
return;
}

void llamaCPP::chatCompletion(
Expand Down Expand Up @@ -365,10 +366,11 @@ void llamaCPP::loadModel(
jsonResp["message"] = "Model loaded successfully";
model_loaded = true;
auto resp = nitro_utils::nitroHttpJsonResponse(jsonResp);
// warmupModel();

LOG_INFO << "Started background task here!";
backgroundThread = std::thread(&llamaCPP::backgroundTask, this);
warmupModel();

callback(resp);
}

Expand Down