Lukas Kreussel

I also played around a bit more and i couldnt get the container working, and i dont know why. All the other containers i build with llama-cpp-python work without any...

I could try later. But i guess i noticed another problem i had, when building my containers via github-actions and then trying to run them locally the containers exit with...

@abetlen Yeah its pretty weird, i played around a bit but can't get it to work even if i use QEMU to force a linux/amd64 platform while building the image...

@abetlen Theoretically QEMU should be able to emulate any cpu features, but i dont know how it is implemented in docker build. They probably create a vm with the cpu...

@abetlen Yup i had a look and tried their image, it runs on my Intel machine but fails with exit code 132 on both my AMD based systems. I will...

@gjmulder Well the images are build on an github-actions-runner which probably uses a virtualized Intel CPU. I then downloaded them an tried to run them on my AMD systems, which...

@gjmulder Alright i ran it locally and on the github-actions-runner. Here are the results: Actions Runner: ``` fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge...

@gjmulder Yes this is probably related. Do you know if it is possible to somehow change what featuresets are used in the compilation of llama.cpp via environment variables? Then i...

@gjmulder Hm this could actually work im gonna try it later and i will just try to disable `avx512` but i dont know what flag to set 😓. But i...

@gjmulder Alrigth i had another look, setting the `CXXFLAGS` or `CFLAGS` is not possible as they are reset in the make file. But if i use cmake i can simply...