After this update, only the setup (first run) can be done successfully, but I cannot run the webui after the second time.
Version Platform Description
OS: Windows 11 Pro x64
WSL2, Ubuntu 22.04.2 LTS
CPU: Intel Core i3-12100
RAM: 48GB
GPU: Intel Arc A750
The following is shown only at the setup run:
Starting SD.Next
01:16:45-376852 INFO Python 3.10.12 on Linux
01:16:45-396292 INFO Version: 81cfb444 Fri Aug 4 16:55:15 2023 +0300
01:16:45-399283 INFO Intel OneAPI Toolkit detected
01:16:45-399979 INFO Installing package: torch==2.0.1a0 torchvision==0.15.2a0 intel_extension_for_pytorch==2.0.110+xpu -f
https://developer.intel.com/ipex-whl-stable-xpu
01:17:17-225477 INFO Disabled extensions: []
01:17:17-226583 INFO Enabled extensions-builtin: ['sd-dynamic-thresholding', 'multidiffusion-upscaler-for-automatic1111', 'Lora', 'ScuNET', 'a1111-sd-webui-lycoris',
'sd-webui-agent-scheduler', 'clip-interrogator-ext', 'LDSR', 'stable-diffusion-webui-images-browser', 'sd-extension-system-info', 'SwinIR',
'stable-diffusion-webui-rembg', 'sd-webui-controlnet']
01:17:17-242863 INFO Enabled extensions: []
Relevant log output
arc@machine-RE2:~/a/automatic$ ./webui.sh
Create and activate python venv
Setting OneAPI environment
:: initializing oneAPI environment ...
webui.sh: BASH_VERSION = 5.1.16(1)-release
args: Using "$@" for setvars.sh arguments:
:: compiler -- latest
/opt/intel/oneapi/compiler/2023.2.0/linux/lib/oclfpga/fpgavars.sh: line 51: export: `Files/Eclipse': not a valid identifier
/opt/intel/oneapi/compiler/2023.2.0/linux/lib/oclfpga/fpgavars.sh: line 51: export: `Adoptium/jre-17.0.7.7-hotspot/bin:/mnt/c/Program': not a valid identifier
/opt/intel/oneapi/compiler/2023.2.0/linux/lib/oclfpga/fpgavars.sh: line 51: export: `Files/Python310/Scripts/:/mnt/c/Program': not a valid identifier
/opt/intel/oneapi/compiler/2023.2.0/linux/lib/oclfpga/fpgavars.sh: line 51: export: `Files/Python310/:/mnt/c/Windows/system32:/mnt/c/Windows:/mnt/c/Windows/System32/Wbem:/mnt/c/Windows/System32/WindowsPowerShell/v1.0/:/mnt/c/Program': not a valid identifier
/opt/intel/oneapi/compiler/2023.2.0/linux/lib/oclfpga/fpgavars.sh: line 51: export: `Files/dotnet/:/mnt/c/Program': not a valid identifier
/opt/intel/oneapi/compiler/2023.2.0/linux/lib/oclfpga/fpgavars.sh: line 51: export: `Files/Git/cmd:/mnt/c/Users/a1/AppData/Local/Microsoft/WindowsApps:/mnt/c/Users/a1/AppData/Roaming/Python/Python310/Scripts:/mnt/c/ADB:/mnt/c/FFMPEG/bin:/snap/bin': not a valid identifier
:: debugger -- latest
:: dev-utilities -- latest
:: dpl -- latest
:: mkl -- latest
:: tbb -- latest
:: oneAPI environment initialized ::
Launching ipexrun launch.py...
/home/arc/a/automatic/venv/lib/python3.10/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: ''If you don't plan on using image functionality from `torchvision.io`, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have `libjpeg` or `libpng` installed before building `torchvision` from source?
warn(
2023-08-05 01:22:34.115894: I tensorflow/core/util/port.cc:110] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2023-08-05 01:22:34.117093: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.
2023-08-05 01:22:34.143210: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.
2023-08-05 01:22:34.143533: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-08-05 01:22:34.590244: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
2023-08-05 01:22:35.180679: I itex/core/wrapper/itex_gpu_wrapper.cc:35] Intel Extension for Tensorflow* GPU backend is loaded.
2023-08-05 01:22:35.221277: W itex/core/ops/op_init.cc:58] Op: _QuantizedMaxPool3D is already registered in Tensorflow
2023-08-05 01:22:35.234937: I itex/core/devices/gpu/itex_gpu_runtime.cc:129] Selected platform: Intel(R) Level-Zero
2023-08-05 01:22:35.235190: I itex/core/devices/gpu/itex_gpu_runtime.cc:154] number of sub-devices is zero, expose root device.
2023-08-05 01:22:35,428 - numexpr.utils - INFO - NumExpr defaulting to 8 threads.
/home/arc/a/automatic/venv/lib/python3.10/site-packages/intel_extension_for_pytorch/launcher.py:102: UserWarning: Backend is not specified, it will automatically default to cpu.
warnings.warn(
2023-08-05 01:22:35,729 - intel_extension_for_pytorch.cpu.launch.launch - WARNING - Neither of ['tcmalloc', 'jemalloc'] memory allocator is found in ['/home/arc/a/automatic/venv/lib/', '/home/arc/.local/lib/', '/usr/local/lib/', '/usr/local/lib64/', '/usr/lib/', '/usr/lib64/', '/usr/lib/x86_64-linux-gnu/'].
2023-08-05 01:22:35,729 - intel_extension_for_pytorch.cpu.launch.launch - INFO - Use 'default' memory allocator. This may drop the performance.
2023-08-05 01:22:35,729 - intel_extension_for_pytorch.cpu.launch.launch - WARNING - 'intel' OpenMP runtime is not found in ['/home/arc/a/automatic/venv/lib/', '/home/arc/.local/lib/', '/usr/local/lib/', '/usr/local/lib64/', '/usr/lib/', '/usr/lib64/', '/usr/lib/x86_64-linux-gnu/'].
2023-08-05 01:22:35,729 - intel_extension_for_pytorch.cpu.launch.launch - INFO - Use 'default' OpenMP runtime.
2023-08-05 01:22:35,730 - intel_extension_for_pytorch.cpu.launch.launch - INFO - Use 'auto' => 'numactl' multi-task manager.
2023-08-05 01:22:35,730 - intel_extension_for_pytorch.cpu.launch.launch - INFO - env: Untouched preset environment variables are not displayed.
2023-08-05 01:22:35,730 - intel_extension_for_pytorch.cpu.launch.launch - INFO - env: OMP_SCHEDULE=STATIC
2023-08-05 01:22:35,730 - intel_extension_for_pytorch.cpu.launch.launch - INFO - env: OMP_PROC_BIND=CLOSE
2023-08-05 01:22:35,730 - intel_extension_for_pytorch.cpu.launch.launch - INFO - env: OMP_NUM_THREADS=4
2023-08-05 01:22:35,730 - intel_extension_for_pytorch.cpu.launch.launch - INFO - cmd: numactl -C 0,2,4,6 -m 0 /home/arc/a/automatic/venv/bin/python3 -u launch.py
numactl: This system does not support NUMA policy
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ /home/arc/a/automatic/venv/bin/ipexrun:8 in <module> │
│ │
│ 5 from intel_extension_for_pytorch.launcher import main │
│ 6 if __name__ == '__main__': │
│ 7 │ sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0]) │
│ ❱ 8 │ sys.exit(main()) │
│ 9 │
│ │
│ /home/arc/a/automatic/venv/lib/python3.10/site-packages/intel_extension_for_pytorch/launcher.py: │
│ 109 in main │
│ │
│ 106 │ │ sys.argv.insert(1, "cpu") │
│ 107 │ args = parser.parse_args() │
│ 108 │ if args.backend == "cpu": │
│ ❱ 109 │ │ cpu_run_main_with_args(args) │
│ 110 │ elif args.backend == "xpu": │
│ 111 │ │ xpu_run_main_with_args(args) │
│ 112 │ else: │
│ │
│ /home/arc/a/automatic/venv/lib/python3.10/site-packages/intel_extension_for_pytorch/cpu/launch/l │
│ aunch.py:453 in run_main_with_args │
│ │
│ 450 │ else: │
│ 451 │ │ launcher = launcher_multi_instances │
│ 452 │ │
│ ❱ 453 │ launcher.launch(args) │
│ 454 │ for x in sorted(set(os.environ.keys()) - env_before): │
│ 455 │ │ logger.debug(f"{x}={os.environ[x]}") │
│ 456 │
│ │
│ /home/arc/a/automatic/venv/lib/python3.10/site-packages/intel_extension_for_pytorch/cpu/launch/l │
│ auncher_multi_instances.py:316 in launch │
│ │
│ 313 │ │ │ │ p = process["process"] │
│ 314 │ │ │ │ p.wait() │
│ 315 │ │ │ │ if p.returncode != 0: │
│ ❱ 316 │ │ │ │ │ raise subprocess.CalledProcessError( │
│ 317 │ │ │ │ │ │ returncode=p.returncode, cmd=process["cmd"] │
│ 318 │ │ │ │ │ ) │
│ 319 │ │ finally: │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
CalledProcessError: Command 'numactl -C 0,2,4,6 -m 0 /home/arc/a/automatic/venv/bin/python3 -u launch.py' returned non-zero exit status 1.
Acknowledgements
[X] I have read the above and searched for existing issues
[X] I confirm that this is classified correctly and its not an extension or diffusers-specific issue
Issue Description
@Disty0
After this update, only the setup (first run) can be done successfully, but I cannot run the webui after the second time.
Version Platform Description
The following is shown only at the setup run:
Relevant log output
Acknowledgements