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

server: fix health/slots endpoint slot state access available race condition

Browse source
This commit is contained in:
Pierrick HYMBERT 2024-02-22 21:47:51 +01:00
parent 41676d9920
commit 016b221549
1 changed files with 5 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

10
examples/server/server.cpp
View file

@ -1400,11 +1400,6 @@ struct llama_server_context
int n_processing_slots = 0;
for (llama_client_slot &slot: slots) {
if (slot.available()) {
n_idle_slots++;
} else {
n_processing_slots++;
}
json slot_data = get_formated_generation(slot);
slot_data["id"] = slot.id;
slot_data["task_id"] = slot.task_id;
@ -1419,6 +1414,11 @@ struct llama_server_context
{"stopped_limit", slot.stopped_limit},
{"stopping_word", slot.stopping_word},
};
if (slot_data["state"] == IDLE) {
n_idle_slots++;
} else {
n_processing_slots++;
}
slots_data.push_back(slot_data);
}
LOG_TEE("task %i - slots data: idle=%i processing=%i\n", task.id, n_idle_slots, n_processing_slots);