Superminaren/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-07 20:47:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

refactor on_sleeping_state

Browse Source
This commit is contained in:
Xuan Son Nguyen
2026-08-19 12:35:18 +02:00
parent 9f710a6e77
commit 5b776fdfe8
3 changed files with 17 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-queue.cpp
+8 -2
View File
@@ -312,7 +312,10 @@ void server_queue::start_loop(int64_t idle_sleep_ms) {
if (should_sleep()) {
QUE_INF("%s", "entering sleeping state\n");
sleeping = true;
callback_sleeping_state(true);
// Call order cb0 -> cb1 -> cb{N}
for (auto & cb : callback_sleeping_state) {
cb(true);
}
req_stop_sleeping = false;
// wait until we are requested to exit sleeping state
condition_tasks.wait(lock, [&]{
@@ -323,7 +326,10 @@ void server_queue::start_loop(int64_t idle_sleep_ms) {
}
QUE_INF("%s", "exiting sleeping state\n");
req_stop_sleeping = false;
callback_sleeping_state(false);
// Call order cb{N} -> cb1 -> cb0
for (size_t i = callback_sleeping_state.size(); i > 0; i--) {
callback_sleeping_state[i - 1](false);
}
sleeping = false;
time_last_task = ggml_time_ms();
condition_tasks.notify_all(); // notify wait_until_no_sleep()