Closed StudioDUzes closed 4 months ago
webui don't start with --no-half --use-cpu all
webui start
9a8a2a47f63c3d9b04c014a715f95d680f461963
Python 3.10.x
Windows
Intel ARC GPUs
sdp
Google Chrome
@echo off set PYTHON= set GIT= set VENV_DIR= set COMMANDLINE_ARGS= --no-half --use-cpu all git pull call webui.bat
no
Already up to date. venv "L:\stable-diffusion-webui-directml\venv\Scripts\Python.exe" fatal: No names found, cannot describe anything. Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] Version: 1.5.1 Commit hash: 9a8a2a47f63c3d9b04c014a715f95d680f461963 Launching Web UI with arguments: --no-half --use-cpu all no module 'xformers'. Processing without... no module 'xformers'. Processing without... No module 'xformers'. Proceeding without it. ╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮ │ L:\stable-diffusion-webui-directml\launch.py:39 in <module> │ │ │ │ 36 │ │ 37 │ │ 38 if __name__ == "__main__": │ │ ❱ 39 │ main() │ │ 40 │ │ │ │ L:\stable-diffusion-webui-directml\launch.py:35 in main │ │ │ │ 32 │ if args.test_server: │ │ 33 │ │ configure_for_tests() │ │ 34 │ │ │ ❱ 35 │ start() │ │ 36 │ │ 37 │ │ 38 if __name__ == "__main__": │ │ │ │ L:\stable-diffusion-webui-directml\modules\launch_utils.py:443 in start │ │ │ │ 440 │ │ 441 def start(): │ │ 442 │ print(f"Launching {'API server' if '--nowebui' in sys.argv else 'Web UI'} with argum │ │ ❱ 443 │ import webui │ │ 444 │ if '--nowebui' in sys.argv: │ │ 445 │ │ webui.api_only() │ │ 446 │ else: │ │ │ │ L:\stable-diffusion-webui-directml\webui.py:54 in <module> │ │ │ │ 51 startup_timer.record("import ldm") │ │ 52 │ │ 53 from modules import extra_networks │ │ ❱ 54 from modules.call_queue import wrap_gradio_gpu_call, wrap_queued_call, queue_lock # noq │ │ 55 │ │ 56 # Truncate version number of nightly/local build of PyTorch to not cause exceptions with │ │ 57 if ".dev" in torch.__version__ or "+git" in torch.__version__: │ │ │ │ L:\stable-diffusion-webui-directml\modules\call_queue.py:6 in <module> │ │ │ │ 3 import threading │ │ 4 import time │ │ 5 │ │ ❱ 6 from modules import shared, progress, errors │ │ 7 │ │ 8 queue_lock = threading.Lock() │ │ 9 │ │ │ │ L:\stable-diffusion-webui-directml\modules\shared.py:756 in <module> │ │ │ │ 753 │ opts.load(config_filename) │ │ 754 │ │ 755 if cmd_opts.backend == 'directml': │ │ ❱ 756 │ directml_do_hijack() │ │ 757 │ │ 758 │ │ 759 class Shared(sys.modules[__name__].__class__): │ │ │ │ L:\stable-diffusion-webui-directml\modules\dml\__init__.py:64 in directml_do_hijack │ │ │ │ 61 │ import modules.dml.hijack │ │ 62 │ from modules.devices import device │ │ 63 │ │ │ ❱ 64 │ if not torch.dml.has_float64_support(device): │ │ 65 │ │ CondFunc('torch.from_numpy', │ │ 66 │ │ │ lambda orig_func, *args, **kwargs: orig_func(args[0].astype('float32')), │ │ 67 │ │ │ lambda *args, **kwargs: args[1].dtype == float) │ │ │ │ L:\stable-diffusion-webui-directml\modules\dml\backend.py:40 in has_float64_support │ │ │ │ 37 │ │ return device.type == "privateuseone" │ │ 38 │ │ │ 39 │ def has_float64_support(device: Optional[rDevice]=None) -> bool: │ │ ❱ 40 │ │ return torch_directml.has_float64_support(get_device(device).index) │ │ 41 │ │ │ 42 │ def device_count() -> int: │ │ 43 │ │ return torch_directml.device_count() │ │ │ │ L:\stable-diffusion-webui-directml\venv\lib\site-packages\torch_directml\device.py:44 in │ │ has_float64_support │ │ │ │ 41 │ torch_directml_native.disable_tiled_resources(is_disabled) │ │ 42 │ │ 43 def has_float64_support(device_id = default_device()): │ │ ❱ 44 │ return torch_directml_native.has_float64_support(device_id) │ │ 45 │ │ 46 def gpu_memory(device_id = default_device(), mb_per_tile = 1): │ │ 47 │ return torch_directml_native.get_gpu_memory(device_id, mb_per_tile) │ ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯ TypeError: has_float64_support(): incompatible function arguments. The following argument types are supported: 1. (arg0: int) -> bool Invoked with: None Appuyez sur une touche pour continuer...
No response
Is there an existing issue for this?
What happened?
webui don't start with --no-half --use-cpu all
Steps to reproduce the problem
What should have happened?
webui start
Version or Commit where the problem happens
9a8a2a47f63c3d9b04c014a715f95d680f461963
What Python version are you running on ?
Python 3.10.x
What platforms do you use to access the UI ?
Windows
What device are you running WebUI on?
Intel ARC GPUs
Cross attention optimization
sdp
What browsers do you use to access the UI ?
Google Chrome
Command Line Arguments
List of extensions
no
Console logs
Additional information
No response