File size: 3,603 Bytes
2540f3b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 |
import html
import threading
import time
from modules import shared, progress, errors
queue_lock = threading.Lock()
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):
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()
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):
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"<div class='error'>{html.escape(error_message)}</div>"]
shared.state.skipped = False
shared.state.interrupted = 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:.2f}s"
if elapsed_m > 0:
elapsed_text = f"{elapsed_m}m "+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 = round(sys_peak/max(sys_total, 1) * 100, 2)
vram_html = f"<p class='vram'>Torch active/reserved: {active_peak}/{reserved_peak} MiB, <wbr>Sys VRAM: {sys_peak}/{sys_total} MiB ({sys_pct}%)</p>"
else:
vram_html = ''
# last item is always HTML
res[-1] += f"<div class='performance'><p class='time'>Time taken: <wbr>{elapsed_text}</p>{vram_html}</div>"
return tuple(res)
return f
|