From 3c23413b8b2ba8a1c2eed07d356fa81e310bb1d2 Mon Sep 17 00:00:00 2001 From: pudepiedj Date: Mon, 26 Feb 2024 13:49:35 +0000 Subject: [PATCH] Adjust print_timings --- cmakescript.sh | 2 -- examples/server/server.cpp | 6 +++--- 2 files changed, 3 insertions(+), 5 deletions(-) diff --git a/cmakescript.sh b/cmakescript.sh index 70e4eece4..6d77f9446 100755 --- a/cmakescript.sh +++ b/cmakescript.sh @@ -11,5 +11,3 @@ else echo "Usage: $0 (Debug|Release)" exit 1 fi - -cd build diff --git a/examples/server/server.cpp b/examples/server/server.cpp index 4b50c9a00..f3867c204 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -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); }