lllyasviel/Fooocus

RuntimeError: No HIP GPUs are available (Linux/AMD)

Open

#1,079 opened on 2023年11月30日

GitHub で見る
 (30 comments) (9 reactions) (0 assignees)Python (48,116 stars) (7,843 forks)batch import
bug (AMD)help wanted

説明

System: Ubuntu 22.04 CPU: i5-6400 GPU: RX 570 8G Environment: Anaconda Python: 3.10.13

I installed with the commands in readme.md (both Linux anaconda and Linux AMD)

but it shows this error log:

Traceback (most recent call last):
  File "/home/octopis/anaconda3/envs/fooocus/lib/python3.10/site-packages/gradio/routes.py", line 488, in run_predict
    output = await app.get_blocks().process_api(
  File "/home/octopis/anaconda3/envs/fooocus/lib/python3.10/site-packages/gradio/blocks.py", line 1431, in process_api
    result = await self.call_function(
  File "/home/octopis/anaconda3/envs/fooocus/lib/python3.10/site-packages/gradio/blocks.py", line 1117, in call_function
    prediction = await utils.async_iteration(iterator)
  File "/home/octopis/anaconda3/envs/fooocus/lib/python3.10/site-packages/gradio/utils.py", line 350, in async_iteration
    return await iterator.__anext__()
  File "/home/octopis/anaconda3/envs/fooocus/lib/python3.10/site-packages/gradio/utils.py", line 343, in __anext__
    return await anyio.to_thread.run_sync(
  File "/home/octopis/anaconda3/envs/fooocus/lib/python3.10/site-packages/anyio/to_thread.py", line 33, in run_sync
    return await get_asynclib().run_sync_in_worker_thread(
  File "/home/octopis/anaconda3/envs/fooocus/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 877, in run_sync_in_worker_thread
    return await future
  File "/home/octopis/anaconda3/envs/fooocus/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 807, in run
    result = context.run(func, *args)
  File "/home/octopis/anaconda3/envs/fooocus/lib/python3.10/site-packages/gradio/utils.py", line 326, in run_sync_iterator_async
    return next(iterator)
  File "/home/octopis/anaconda3/envs/fooocus/lib/python3.10/site-packages/gradio/utils.py", line 695, in gen_wrapper
    yield from f(*args, **kwargs)
  File "/home/octopis/Fooocus/webui.py", line 25, in generate_clicked
    import fcbh.model_management as model_management
  File "/home/octopis/Fooocus/backend/headless/fcbh/model_management.py", line 114, in <module>
    total_vram = get_total_memory(get_torch_device()) / (1024 * 1024)
  File "/home/octopis/Fooocus/backend/headless/fcbh/model_management.py", line 83, in get_torch_device
    return torch.device(torch.cuda.current_device())
  File "/home/octopis/anaconda3/envs/fooocus/lib/python3.10/site-packages/torch/cuda/__init__.py", line 674, in current_device
    _lazy_init()
  File "/home/octopis/anaconda3/envs/fooocus/lib/python3.10/site-packages/torch/cuda/__init__.py", line 247, in _lazy_init
    torch._C._cuda_init()
RuntimeError: No HIP GPUs are available

I saw someone is discussing the same error log in ComfyUI and I tried what they said: downgrade Pytorch, ROCm to 5.4.2. but still got the same error.

EDIT: forgot to mention, the Web UI does appear, but the error message just print out after trying to generate things. I don't know if this information helps, but I'll leave it here.

コントリビューターガイド