Is there an existing issue for this?
What happened?
After following the "Automatic Installation" instructions from the wiki for AMD cards, I get the following error:
Traceback (most recent call last):
File "/home/basil/stable-diffusion-webui/launch.py", line 355, in <module>
prepare_environment()
File "/home/basil/stable-diffusion-webui/launch.py", line 260, in prepare_environment
run_python("import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'")
File "/home/basil/stable-diffusion-webui/launch.py", line 121, in run_python
return run(f'"{python}" -c "{code}"', desc, errdesc)
File "/home/basil/stable-diffusion-webui/launch.py", line 97, in run
raise RuntimeError(message)
RuntimeError: Error running command.
Command: "/home/basil/stable-diffusion-webui/venv/bin/python3" -c "import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'"
Error code: 1
stdout: <empty>
stderr: Traceback (most recent call last):
File "<string>", line 1, in <module>
AssertionError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check
If I pass --skip-torch-cuda-test, I then get the following error:
Error completing request
Arguments: ('task(ry0zf9rah332ozo)', 'caaa', '(low quality, worst quality:1.4),(bad_prompt:0.8), (monochrome:1.1), (greyscale)', [], 28, 16, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 768, 512, False, 0.7, 2, 'Latent', 0, 0, 0, [], 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', 0, '', 0, '', True, False, False, False, 0) {}
Traceback (most recent call last):
File "/home/basil/stable-diffusion-webui/modules/call_queue.py", line 56, in f
res = list(func(*args, **kwargs))
File "/home/basil/stable-diffusion-webui/modules/call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "/home/basil/stable-diffusion-webui/modules/txt2img.py", line 56, in txt2img
processed = process_images(p)
File "/home/basil/stable-diffusion-webui/modules/processing.py", line 503, in process_images
res = process_images_inner(p)
File "/home/basil/stable-diffusion-webui/modules/processing.py", line 642, in process_images_inner
uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps, cached_uc)
File "/home/basil/stable-diffusion-webui/modules/processing.py", line 587, in get_conds_with_caching
cache[1] = function(shared.sd_model, required_prompts, steps)
File "/home/basil/stable-diffusion-webui/modules/prompt_parser.py", line 140, in get_learned_conditioning
conds = model.get_learned_conditioning(texts)
File "/home/basil/stable-diffusion-webui/repositories/stable-diffusion-stability-ai/ldm/models/diffusion/ddpm.py", line 669, in get_learned_conditioning
c = self.cond_stage_model(c)
File "/home/basil/stable-diffusion-webui/venv/lib64/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/basil/stable-diffusion-webui/modules/sd_hijack_clip.py", line 229, in forward
z = self.process_tokens(tokens, multipliers)
File "/home/basil/stable-diffusion-webui/modules/sd_hijack_clip.py", line 254, in process_tokens
z = self.encode_with_transformers(tokens)
File "/home/basil/stable-diffusion-webui/modules/sd_hijack_clip.py", line 302, in encode_with_transformers
outputs = self.wrapped.transformer(input_ids=tokens, output_hidden_states=-opts.CLIP_stop_at_last_layers)
File "/home/basil/stable-diffusion-webui/venv/lib64/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/basil/stable-diffusion-webui/venv/lib64/python3.10/site-packages/transformers/models/clip/modeling_clip.py", line 811, in forward
return self.text_model(
File "/home/basil/stable-diffusion-webui/venv/lib64/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/basil/stable-diffusion-webui/venv/lib64/python3.10/site-packages/transformers/models/clip/modeling_clip.py", line 721, in forward
encoder_outputs = self.encoder(
File "/home/basil/stable-diffusion-webui/venv/lib64/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/basil/stable-diffusion-webui/venv/lib64/python3.10/site-packages/transformers/models/clip/modeling_clip.py", line 650, in forward
layer_outputs = encoder_layer(
File "/home/basil/stable-diffusion-webui/venv/lib64/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/basil/stable-diffusion-webui/venv/lib64/python3.10/site-packages/transformers/models/clip/modeling_clip.py", line 378, in forward
hidden_states = self.layer_norm1(hidden_states)
File "/home/basil/stable-diffusion-webui/venv/lib64/python3.10/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/basil/stable-diffusion-webui/venv/lib64/python3.10/site-packages/torch/nn/modules/normalization.py", line 190, in forward
return F.layer_norm(
File "/home/basil/stable-diffusion-webui/venv/lib64/python3.10/site-packages/torch/nn/functional.py", line 2515, in layer_norm
return torch.layer_norm(input, normalized_shape, weight, bias, eps, torch.backends.cudnn.enabled)
RuntimeError: "LayerNormKernelImpl" not implemented for 'Half'
If I then pass --skip-torch-cuda-test --precision full --no-half, the UI begins using my CPU to generate images instead of using my GPU like it should.
With the Docker method, I get the same error about Torch not being able to use the GPU, add --skip-torch-cuda, etc.
Steps to reproduce the problem
- Follow the instructions here.
What should have happened?
The UI should have ran normally and utilized my GPU to generate images.
Commit where the problem happens
22bcc7b
What platforms do you use to access the UI ?
Linux
What browsers do you use to access the UI ?
Mozilla Firefox
Command Line Arguments
./webui.sh
./webui.sh --skip-torch-cuda-test
./webui.sh --skip-torch-cuda-test --precision full --no-half
List of extensions
No
Console logs
./webui.sh
################################################################
Install script for stable-diffusion + Web UI
Tested on Debian 11 (Bullseye)
################################################################
################################################################
Running on basil user
################################################################
################################################################
Repo already cloned, using it as install directory
################################################################
################################################################
Create and activate python venv
################################################################
################################################################
Launching launch.py...
################################################################
Python 3.10.10 (main, Mar 01 2023, 21:10:14) [GCC]
Commit hash: 22bcc7be428c94e9408f589966c2040187245d81
Installing torch and torchvision
Looking in indexes: https://pypi.org/simple, https://download.pytorch.org/whl/rocm5.2
Collecting torch
Using cached torch-2.0.0-cp310-cp310-manylinux1_x86_64.whl (619.9 MB)
Collecting torchvision
Using cached torchvision-0.15.1-cp310-cp310-manylinux1_x86_64.whl (6.0 MB)
Collecting nvidia-cudnn-cu11==8.5.0.96
Using cached nvidia_cudnn_cu11-8.5.0.96-2-py3-none-manylinux1_x86_64.whl (557.1 MB)
Collecting nvidia-cufft-cu11==10.9.0.58
Using cached nvidia_cufft_cu11-10.9.0.58-py3-none-manylinux1_x86_64.whl (168.4 MB)
Collecting nvidia-cusolver-cu11==11.4.0.1
Using cached nvidia_cusolver_cu11-11.4.0.1-2-py3-none-manylinux1_x86_64.whl (102.6 MB)
Collecting nvidia-nccl-cu11==2.14.3
Using cached nvidia_nccl_cu11-2.14.3-py3-none-manylinux1_x86_64.whl (177.1 MB)
Collecting typing-extensions
Using cached typing_extensions-4.5.0-py3-none-any.whl (27 kB)
Collecting nvidia-nvtx-cu11==11.7.91
Using cached nvidia_nvtx_cu11-11.7.91-py3-none-manylinux1_x86_64.whl (98 kB)
Collecting networkx
Using cached networkx-3.1-py3-none-any.whl (2.1 MB)
Collecting nvidia-cuda-cupti-cu11==11.7.101
Using cached nvidia_cuda_cupti_cu11-11.7.101-py3-none-manylinux1_x86_64.whl (11.8 MB)
Collecting nvidia-curand-cu11==10.2.10.91
Using cached nvidia_curand_cu11-10.2.10.91-py3-none-manylinux1_x86_64.whl (54.6 MB)
Collecting nvidia-cusparse-cu11==11.7.4.91
Using cached nvidia_cusparse_cu11-11.7.4.91-py3-none-manylinux1_x86_64.whl (173.2 MB)
Collecting triton==2.0.0
Using cached https://download.pytorch.org/whl/triton-2.0.0-1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (63.3 MB)
Collecting filelock
Using cached filelock-3.10.7-py3-none-any.whl (10 kB)
Collecting jinja2
Using cached https://download.pytorch.org/whl/Jinja2-3.1.2-py3-none-any.whl (133 kB)
Collecting nvidia-cublas-cu11==11.10.3.66
Using cached nvidia_cublas_cu11-11.10.3.66-py3-none-manylinux1_x86_64.whl (317.1 MB)
Collecting sympy
Using cached https://download.pytorch.org/whl/sympy-1.11.1-py3-none-any.whl (6.5 MB)
Collecting nvidia-cuda-runtime-cu11==11.7.99
Using cached nvidia_cuda_runtime_cu11-11.7.99-py3-none-manylinux1_x86_64.whl (849 kB)
Collecting nvidia-cuda-nvrtc-cu11==11.7.99
Using cached nvidia_cuda_nvrtc_cu11-11.7.99-2-py3-none-manylinux1_x86_64.whl (21.0 MB)
Requirement already satisfied: wheel in ./venv/lib/python3.10/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch) (0.40.0)
Requirement already satisfied: setuptools in ./venv/lib/python3.10/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch) (65.5.0)
Collecting cmake
Using cached cmake-3.26.1-py2.py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (24.0 MB)
Collecting lit
Using cached lit-16.0.0-py3-none-any.whl
Collecting requests
Using cached requests-2.28.2-py3-none-any.whl (62 kB)
Collecting pillow!=8.3.*,>=5.3.0
Using cached Pillow-9.5.0-cp310-cp310-manylinux_2_28_x86_64.whl (3.4 MB)
Collecting numpy
Using cached numpy-1.24.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.3 MB)
Collecting MarkupSafe>=2.0
Using cached https://download.pytorch.org/whl/MarkupSafe-2.1.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (25 kB)
Collecting charset-normalizer<4,>=2
Using cached charset_normalizer-3.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (199 kB)
Collecting idna<4,>=2.5
Using cached https://download.pytorch.org/whl/idna-3.4-py3-none-any.whl (61 kB)
Collecting urllib3<1.27,>=1.21.1
Using cached urllib3-1.26.15-py2.py3-none-any.whl (140 kB)
Collecting certifi>=2017.4.17
Using cached https://download.pytorch.org/whl/certifi-2022.12.7-py3-none-any.whl (155 kB)
Collecting mpmath>=0.19
Using cached mpmath-1.3.0-py3-none-any.whl (536 kB)
Installing collected packages: mpmath, lit, cmake, urllib3, typing-extensions, sympy, pillow, nvidia-nvtx-cu11, nvidia-nccl-cu11, nvidia-cusparse-cu11, nvidia-curand-cu11, nvidia-cufft-cu11, nvidia-cuda-runtime-cu11, nvidia-cuda-nvrtc-cu11, nvidia-cuda-cupti-cu11, nvidia-cublas-cu11, numpy, networkx, MarkupSafe, idna, filelock, charset-normalizer, certifi, requests, nvidia-cusolver-cu11, nvidia-cudnn-cu11, jinja2, triton, torch, torchvision
Successfully installed MarkupSafe-2.1.2 certifi-2022.12.7 charset-normalizer-3.1.0 cmake-3.26.1 filelock-3.10.7 idna-3.4 jinja2-3.1.2 lit-16.0.0 mpmath-1.3.0 networkx-3.1 numpy-1.24.2 nvidia-cublas-cu11-11.10.3.66 nvidia-cuda-cupti-cu11-11.7.101 nvidia-cuda-nvrtc-cu11-11.7.99 nvidia-cuda-runtime-cu11-11.7.99 nvidia-cudnn-cu11-8.5.0.96 nvidia-cufft-cu11-10.9.0.58 nvidia-curand-cu11-10.2.10.91 nvidia-cusolver-cu11-11.4.0.1 nvidia-cusparse-cu11-11.7.4.91 nvidia-nccl-cu11-2.14.3 nvidia-nvtx-cu11-11.7.91 pillow-9.5.0 requests-2.28.2 sympy-1.11.1 torch-2.0.0 torchvision-0.15.1 triton-2.0.0 typing-extensions-4.5.0 urllib3-1.26.15
Traceback (most recent call last):
File "/home/basil/stable-diffusion-webui/launch.py", line 355, in <module>
prepare_environment()
File "/home/basil/stable-diffusion-webui/launch.py", line 260, in prepare_environment
run_python("import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'")
File "/home/basil/stable-diffusion-webui/launch.py", line 121, in run_python
return run(f'"{python}" -c "{code}"', desc, errdesc)
File "/home/basil/stable-diffusion-webui/launch.py", line 97, in run
raise RuntimeError(message)
RuntimeError: Error running command.
Command: "/home/basil/stable-diffusion-webui/venv/bin/python3" -c "import torch; assert torch.cuda.is_available(), 'Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check'"
Error code: 1
stdout: <empty>
stderr: Traceback (most recent call last):
File "<string>", line 1, in <module>
AssertionError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this checkAdditional information
When I was on Arch Linux (about a month ago), the "Automatic Installation" instructions worked fine; the UI would install pytorch+rocm normally and the UI would generate images normally using my GPU.
I am now on openSUSE Tumbleweed. My GPU is a 6700 XT.
Another thing worth noting: at the bottom of the UI, the PyTorch version is torch: 2.0.0+cu117.
Is there an existing issue for this?
What happened?
After following the "Automatic Installation" instructions from the wiki for AMD cards, I get the following error:
If I pass
--skip-torch-cuda-test, I then get the following error:If I then pass
--skip-torch-cuda-test --precision full --no-half, the UI begins using my CPU to generate images instead of using my GPU like it should.With the Docker method, I get the same error about Torch not being able to use the GPU, add
--skip-torch-cuda, etc.Steps to reproduce the problem
What should have happened?
The UI should have ran normally and utilized my GPU to generate images.
Commit where the problem happens
22bcc7b
What platforms do you use to access the UI ?
Linux
What browsers do you use to access the UI ?
Mozilla Firefox
Command Line Arguments
List of extensions
No
Console logs
Additional information
When I was on Arch Linux (about a month ago), the "Automatic Installation" instructions worked fine; the UI would install pytorch+rocm normally and the UI would generate images normally using my GPU.
I am now on openSUSE Tumbleweed. My GPU is a 6700 XT.
Another thing worth noting: at the bottom of the UI, the PyTorch version is
torch: 2.0.0+cu117.