npu启动stable-diffusion-webui报错

一、问题现象（附报错日志上下文）：
参考https://github.com/wangshuai09/stable-diffusion-webui/wiki/Install-and-run-on-Ascend-NPUs
手动安装启动stable-diffusion-webui报错

二、软件版本:
-- CANN 版本 (e.g., CANN 3.0.x，5.x.x):  8.0.RC2
--Tensorflow/Pytorch/MindSpore 版本: torch: 2.1.0 torch-npu: 2.1.0
--Python 版本 (e.g., Python 3.7.5):Python 3.10.2
--操作系统版本 (e.g., Ubuntu 18.04):Ubuntu 20.04 LTS

三、测试步骤：
python -m venv venv
#IB4AN5 .\venv\Scripts\activate
source ./venv/bin/activate
pip install torch==2.1.0 torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
pip install torch_npu==2.1.0
#pip install https://github.com/openai/CLIP/archive/d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip --prefer-binary
pip install CLIP-d50d76daa670286dd6cacf3bcd80b5e4823fc8e1.zip --prefer-binary
#pip install https://github.com/mlfoundations/open_clip/archive/bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b.zip
pip install open_clip-bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b.zip
pip install -U -I --no-deps xformers==0.0.23.post1
pip install install ngrok
mkdir repositories 
git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui-assets.git stable-diffusion-webui-assets
git -C stable-diffusion-webui-assets checkout 6f7db241d2f8ba7457bac5ca9753331f0c266917
git clone https://github.com/Stability-AI/stablediffusion.git stable-diffusion-stability-ai
git -C stable-diffusion-stability-ai checkout cf1d67a6fd5ea1aa600c4df58e5b47da45f6bdbf
git clone https://github.com/Stability-AI/generative-models.git generative-models
git -C generative-models checkout 45c443b316737a4ab6e40413d7794a7f5657c19f
git clone https://github.com/crowsonkb/k-diffusion.git k-diffusion
git -C k-diffusion checkout ab527a9a6d347f364e3d185ba6d714e22d80cb3c
git clone https://github.com/salesforce/BLIP.git BLIP 
git -C BLIP checkout 48211a1594f1321b00f14c9f7a5b4813144b2fb9
pip install -r requirements.txt
pip install -r requirements_npu.txt

./webui.sh --listen --skip-torch-cuda-test --no-half

四、日志信息:
################################################################
Clone stable-diffusion-webui
################################################################
Cloning into 'stable-diffusion-webui'...
remote: Enumerating objects: 34648, done.
remote: Counting objects: 100% (102/102), done.
remote: Compressing objects: 100% (80/80), done.
remote: Total 34648 (delta 48), reused 57 (delta 21), pack-reused 34546 (from 1)
Receiving objects: 100% (34648/34648), 35.41 MiB | 8.07 MiB/s, done.
Resolving deltas: 100% (24207/24207), done.

################################################################
python venv already activate or run without venv: /ai/zxy/stable-diffusion-webui/venv
################################################################

################################################################
Launching launch.py...
################################################################
glibc version is 2.31
Cannot locate TCMalloc. Do you have tcmalloc or google-perftool installed on your system? (improves CPU memory usage)
Python 3.10.2 (main, Nov 11 2024, 08:50:31) [GCC 9.4.0]
Version: v1.10.1
Commit hash: 82a973c04367123ae98bd9abdf80d9eda9b910e2
Cloning assets into /ai/zxy/stable-diffusion-webui/stable-diffusion-webui/repositories/stable-diffusion-webui-assets...
Cloning into '/ai/zxy/stable-diffusion-webui/stable-diffusion-webui/repositories/stable-diffusion-webui-assets'...
remote: Enumerating objects: 20, done.
remote: Counting objects: 100% (20/20), done.
remote: Compressing objects: 100% (18/18), done.
remote: Total 20 (delta 0), reused 20 (delta 0), pack-reused 0 (from 0)
Unpacking objects: 100% (20/20), 132.68 KiB | 404.00 KiB/s, done.
Cloning Stable Diffusion into /ai/zxy/stable-diffusion-webui/stable-diffusion-webui/repositories/stable-diffusion-stability-ai...
Cloning into '/ai/zxy/stable-diffusion-webui/stable-diffusion-webui/repositories/stable-diffusion-stability-ai'...
remote: Enumerating objects: 580, done.
remote: Counting objects: 100% (3/3), done.
remote: Compressing objects: 100% (3/3), done.
remote: Total 580 (delta 0), reused 1 (delta 0), pack-reused 577 (from 1)
Receiving objects: 100% (580/580), 73.44 MiB | 8.77 MiB/s, done.
Resolving deltas: 100% (281/281), done.
Cloning Stable Diffusion XL into /ai/zxy/stable-diffusion-webui/stable-diffusion-webui/repositories/generative-models...
Cloning into '/ai/zxy/stable-diffusion-webui/stable-diffusion-webui/repositories/generative-models'...
remote: Enumerating objects: 1064, done.
remote: Counting objects: 100% (477/477), done.
remote: Compressing objects: 100% (124/124), done.
remote: Total 1064 (delta 376), reused 353 (delta 353), pack-reused 587 (from 1)
Receiving objects: 100% (1064/1064), 53.60 MiB | 9.06 MiB/s, done.
Resolving deltas: 100% (562/562), done.
Cloning K-diffusion into /ai/zxy/stable-diffusion-webui/stable-diffusion-webui/repositories/k-diffusion...
Cloning into '/ai/zxy/stable-diffusion-webui/stable-diffusion-webui/repositories/k-diffusion'...
remote: Enumerating objects: 1345, done.
remote: Counting objects: 100% (646/646), done.
remote: Compressing objects: 100% (86/86), done.
remote: Total 1345 (delta 604), reused 561 (delta 560), pack-reused 699 (from 1)
Receiving objects: 100% (1345/1345), 239.07 KiB | 492.00 KiB/s, done.
Resolving deltas: 100% (944/944), done.
Cloning BLIP into /ai/zxy/stable-diffusion-webui/stable-diffusion-webui/repositories/BLIP...
Cloning into '/ai/zxy/stable-diffusion-webui/stable-diffusion-webui/repositories/BLIP'...
remote: Enumerating objects: 277, done.
remote: Counting objects: 100% (183/183), done.
remote: Compressing objects: 100% (46/46), done.
remote: Total 277 (delta 145), reused 137 (delta 137), pack-reused 94 (from 1)
Receiving objects: 100% (277/277), 7.04 MiB | 5.80 MiB/s, done.
Resolving deltas: 100% (152/152), done.
Installing requirements
Launching Web UI with arguments: --listen --skip-torch-cuda-test --no-half
/ai/zxy/stable-diffusion-webui/venv/lib/python3.10/site-packages/timm/models/layers/__init__.py:48: FutureWarning: Importing from timm.models.layers is deprecated, please import via timm.layers
  warnings.warn(f"Importing from {__name__} is deprecated, please import via timm.layers", FutureWarning)
No module 'xformers'. Proceeding without it.
Traceback (most recent call last):
  File "/ai/zxy/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch_npu/__init__.py", line 14, in <module>
    import torch_npu.npu
  File "/ai/zxy/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch_npu/npu/__init__.py", line 110, in <module>
    from .utils import (synchronize, device_count, can_device_access_peer, set_device, current_device, get_device_name,
  File "/ai/zxy/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch_npu/npu/utils.py", line 11, in <module>
    import torch_npu._C
ImportError: /lib/aarch64-linux-gnu/libgomp.so.1: cannot allocate memory in static TLS block
Traceback (most recent call last):
  File "/ai/zxy/stable-diffusion-webui/stable-diffusion-webui/launch.py", line 48, in <module>
    main()
  File "/ai/zxy/stable-diffusion-webui/stable-diffusion-webui/launch.py", line 44, in main
    start()
  File "/ai/zxy/stable-diffusion-webui/stable-diffusion-webui/modules/launch_utils.py", line 465, in start
    import webui
  File "/ai/zxy/stable-diffusion-webui/stable-diffusion-webui/webui.py", line 13, in <module>
    initialize.imports()
  File "/ai/zxy/stable-diffusion-webui/stable-diffusion-webui/modules/initialize.py", line 36, in imports
    shared_init.initialize()
  File "/ai/zxy/stable-diffusion-webui/stable-diffusion-webui/modules/shared_init.py", line 17, in initialize
    from modules import options, shared_options
  File "/ai/zxy/stable-diffusion-webui/stable-diffusion-webui/modules/shared_options.py", line 4, in <module>
    from modules import localization, ui_components, shared_items, shared, interrogate, shared_gradio_themes, util, sd_emphasis
  File "/ai/zxy/stable-diffusion-webui/stable-diffusion-webui/modules/interrogate.py", line 13, in <module>
    from modules import devices, paths, shared, lowvram, modelloader, errors, torch_utils
  File "/ai/zxy/stable-diffusion-webui/stable-diffusion-webui/modules/devices.py", line 6, in <module>
    from modules import errors, shared, npu_specific
  File "/ai/zxy/stable-diffusion-webui/stable-diffusion-webui/modules/npu_specific.py", line 31, in <module>
    has_npu = check_for_npu()
  File "/ai/zxy/stable-diffusion-webui/stable-diffusion-webui/modules/npu_specific.py", line 10, in check_for_npu
    import torch_npu
  File "/ai/zxy/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch_npu/__init__.py", line 37, in <module>
    import torch_npu.npu.amp
  File "/ai/zxy/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch_npu/npu/__init__.py", line 110, in <module>
    from .utils import (synchronize, device_count, can_device_access_peer, set_device, current_device, get_device_name,
  File "/ai/zxy/stable-diffusion-webui/venv/lib/python3.10/site-packages/torch_npu/npu/utils.py", line 11, in <module>
    import torch_npu._C
ImportError: /lib/aarch64-linux-gnu/libgomp.so.1: cannot allocate memory in static TLS block

pip install --upgrade torch-npu
升级到2.4.0后还是
ImportError: /lib/aarch64-linux-gnu/libGLdispatch.so.0: cannot allocate memory in static TLS block
[ERROR] 2024-11-14-06:14:22 (PID:1530, Device:-1, RankID:-1) ERR99999 UNKNOWN applicaiton exception

export LD_PRELOAD=/lib/aarch64-linux-gnu/libGLdispatch.so.0:$LD_PRELOAD

Ascend/pytorch

内容风险标识

评论 (2)

Ascend/pytorch .gitee-modal { width: 500px !important; }

内容风险标识