Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0!

报错内容

在运行 stable-diffusion-webui-docker 过程中，依然存在 Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! 的报错，具体如下：

auto-1  |       File "/stable-diffusion-webui/modules/sd_hijack.py", line 348, in forward
auto-1  |         inputs_embeds = self.wrapped(input_ids)
auto-1  |       File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
auto-1  |         return self._call_impl(*args, **kwargs)
auto-1  |       File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
auto-1  |         return forward_call(*args, **kwargs)
auto-1  |       File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/sparse.py", line 163, in forward
auto-1  |         return F.embedding(
auto-1  |       File "/opt/conda/lib/python3.10/site-packages/torch/nn/functional.py", line 2264, in embedding
auto-1  |         return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
auto-1  |     RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument index in method wrapper_CUDA__index_select)

产生原因

运行 stable-diffusion-webui 时遇到过该报错，我在 docker-compose.yaml 启动命令中指定了 --divice-id 0 后恢复正常，但是，在指定 ollama 的 gpu device 为1后，再运行 ollama 和 stable-diffusion-webui，依然存在该报错。而 stable-diffusion-webui 中的启动，的确是指定了 device id

 services:
  download:
    build: ./services/download/
    profiles: ["download"]
    volumes:
      - *v1

  auto: &automatic
    <<: *base_service
    profiles: ["auto"]
    build: ./services/AUTOMATIC1111
    image: sd-auto:78
    environment:
      - CLI_ARGS=--allow-code --medvram --xformers --enable-insecure-extension-access --api --device-id 0

而在 &base-service 中，只提供了 device_ids: ['0']

x-base_service: &base_service
    ports:
      - "${WEBUI_PORT:-7860}:7860"
    volumes:
      - &v1 /mnt/data/dify-models/plugins/stable-diffusion/data:/data
      - &v2 /mnt/data/dify-models/plugins/stable-diffusion/output:/output
    stop_signal: SIGKILL
    tty: true
    deploy:
      resources:
        reservations:
          devices:
              - driver: nvidia
                device_ids: ['0']
                capabilities: [compute, utility]

解决方案

修改为 device_ids: ['0', '1'] 后能够正常使用