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

Adjust print_timings

Browse source
This commit is contained in:
pudepiedj 2024-02-26 13:49:35 +00:00
parent 2768634743
commit 3c23413b8b
2 changed files with 3 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

2
cmakescript.sh
View file

@ -11,5 +11,3 @@ else
echo "Usage: $0 (Debug|Release)"
exit 1
fi
cd build

6
examples/server/server.cpp
View file

@ -1610,7 +1610,7 @@ struct llama_server_context
int n_processing_slots = 0;
for (llama_client_slot &slot: slots) {
json slot_data = get_formated_generation(slot);
json slot_data = get_formatted_generation(slot);
slot_data["id"] = slot.id;
slot_data["task_id"] = slot.task_id;
slot_data["state"] = slot.state;
@ -1811,7 +1811,7 @@ struct llama_server_context
if (slot.state == IDLE && slot.command == LOAD_PROMPT && !has_prompt && !slot.infill)
{
slot.release();
slot.print_timings(slot, skvinteract);
slot.print_timings();
send_final_response(slot);
continue;
}
@ -2140,7 +2140,7 @@ struct llama_server_context
if (!process_token(result, slot))
{
slot.release();
slot.print_timings(slot, skvinteract);
slot.print_timings();
send_final_response(slot);
metrics.on_prediction(slot);
}