mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-06-27 03:55:20 +00:00
@ -1880,6 +1880,7 @@ struct server_context {
|
||||
if (slot.state == SLOT_STATE_STARTED) {
|
||||
slot.t_start_process_prompt = ggml_time_us();
|
||||
slot.t_start_generation = 0;
|
||||
|
||||
slot.n_past = 0;
|
||||
slot.n_prompt_tokens = prompt_tokens.size();
|
||||
slot.state = SLOT_STATE_PROCESSING_PROMPT;
|
||||
|
Reference in New Issue
Block a user