import os.path from functools import wraps import html import time from modules import shared, progress, errors, devices, fifo_lock, profiling queue_lock = fifo_lock.FIFOLock() def wrap_queued_call(func): def f(*args, **kwargs): with queue_lock: res = func(*args, **kwargs) return res return f def wrap_gradio_gpu_call(func, extra_outputs=None): @wraps(func) def f(*args, **kwargs): # if the first argument is a string that says "task(...)", it is treated as a job id if args and type(args[0]) == str and args[0].startswith("task(") and args[0].endswith(")"): id_task = args[0] progress.add_task_to_queue(id_task) else: id_task = None with queue_lock: shared.state.begin(job=id_task) progress.start_task(id_task) try: res = func(*args, **kwargs) progress.record_results(id_task, res) finally: progress.finish_task(id_task) shared.state.end() return res return wrap_gradio_call(f, extra_outputs=extra_outputs, add_stats=True) def wrap_gradio_call(func, extra_outputs=None, add_stats=False): @wraps(func) def f(*args, extra_outputs_array=extra_outputs, **kwargs): run_memmon = shared.opts.memmon_poll_rate > 0 and not shared.mem_mon.disabled and add_stats if run_memmon: shared.mem_mon.monitor() t = time.perf_counter() try: res = list(func(*args, **kwargs)) except Exception as e: # When printing out our debug argument list, # do not print out more than a 100 KB of text max_debug_str_len = 131072 message = "Error completing request" arg_str = f"Arguments: {args} {kwargs}"[:max_debug_str_len] if len(arg_str) > max_debug_str_len: arg_str += f" (Argument list truncated at {max_debug_str_len}/{len(arg_str)} characters)" errors.report(f"{message}\n{arg_str}", exc_info=True) shared.state.job = "" shared.state.job_count = 0 if extra_outputs_array is None: extra_outputs_array = [None, ''] error_message = f'{type(e).__name__}: {e}' res = extra_outputs_array + [f"
{html.escape(error_message)}
"] devices.torch_gc() shared.state.skipped = False shared.state.interrupted = False shared.state.stopping_generation = False shared.state.job_count = 0 if not add_stats: return tuple(res) elapsed = time.perf_counter() - t elapsed_m = int(elapsed // 60) elapsed_s = elapsed % 60 elapsed_text = f"{elapsed_s:.1f} sec." if elapsed_m > 0: elapsed_text = f"{elapsed_m} min. "+elapsed_text if run_memmon: mem_stats = {k: -(v//-(1024*1024)) for k, v in shared.mem_mon.stop().items()} active_peak = mem_stats['active_peak'] reserved_peak = mem_stats['reserved_peak'] sys_peak = mem_stats['system_peak'] sys_total = mem_stats['total'] sys_pct = sys_peak/max(sys_total, 1) * 100 toltip_a = "Active: peak amount of video memory used during generation (excluding cached data)" toltip_r = "Reserved: total amount of video memory allocated by the Torch library " toltip_sys = "System: peak amount of video memory allocated by all running programs, out of total capacity" text_a = f"A: {active_peak/1024:.2f} GB" text_r = f"R: {reserved_peak/1024:.2f} GB" text_sys = f"Sys: {sys_peak/1024:.1f}/{sys_total/1024:g} GB ({sys_pct:.1f}%)" vram_html = f"

{text_a}, {text_r}, {text_sys}

" else: vram_html = '' if shared.opts.profiling_enable and os.path.exists(shared.opts.profiling_filename): profiling_html = f"

[ Profile ]

" else: profiling_html = '' # last item is always HTML res[-1] += f"

Time taken: {elapsed_text}

{vram_html}{profiling_html}
" return tuple(res) return f