Hi All,
I’m trying to get some validation if it works with this hardware combination when using docker.
System info:
Amd Ryzen 5600G
Intel Arc B580
Ubuntu 24.10 with passthru from Proxmox
Resizeable rombar is set fine
Docker
Comfyui on ubuntu using pytorch in the same Ubuntu vm looks to run fine with some bugs here and there.
For some reason, I’ve never gotten the docker versions of the comfyui/stable diffusion working.
Going back to trying to get things in docker last night … this illegal instruction/core dump looks to come in in any docker image I try with pytorch/comfyui/sd/etc. Ollama in docker works fine and sees my intel arc b580.
docker run --rm -it --privileged -v /dev/dri:/dev/dri --ipc=host intel/intel-extension-for-pytorch:2.7.10-xpu bash
root@9c8494f7a126:/# python -c “import torch; import intel_extension_for_pytorch as ipex; print(torch.version); print(ipex.version); [print(f’[{i}]: {torch.xpu.get_device_properties(i)}') for i in range(torch.xpu.device_count())];”
[W517 00:16:02.736196261 OperatorEntry.cpp:154] Warning: Warning only once for all operators, other operators may also be overridden.
Overriding a previously registered kernel for the same operator and the same dispatch key
operator: aten::geometric_(Tensor(a!) self, float p, *, Generator? generator=None) → Tensor(a!)
registered at /pytorch/build/aten/src/ATen/RegisterSchema.cpp:6
dispatch key: XPU
previous kernel: registered at /pytorch/aten/src/ATen/VmapModeRegistrations.cpp:37
new kernel: registered at /build/intel-pytorch-extension/build/Release/csrc/gpu/csrc/gpu/xpu/ATen/RegisterXPU_0.cpp:186 (function operator())
Illegal instruction (core dumped)