Martin Evans

Thanks for confirming that

If you clone this repo and run the example project does it work, or do you get the same error?

One of the things that has changed from 7->8 is that llamasharp will try to autodetect certain CPU features (AVX512) and use a better binary if it detects them. So...

Has this been resolved with the release of v0.9.1?

I'll close this for now, since the issue was hopefully resolved in 0.9.1. Please don't hesitate to re-open if you're still having issues!

Checking I understand the issue correctly: - If you run it with just the CUDA backend, it crashes because it can't load the AVX512 llama.dll. - If you run it...

Originally they weren't meant to be installed together, since it then wasn't clear which binaries should be used. However we now have the runtime detection which should probe your system...

> When I load a model on the CPU with GpuLayerCount equals to 0, the cuda backend is loaded That's how it's meant to work - if the CUDA binaries...

What does the log call back show for you (see [this comment](https://github.com/SciSharp/LLamaSharp/issues/456#issuecomment-2435526377) just above for how to add the callback)?

There's something a bit odd going on here, your log shows that it tried to load things in this order: > Info: Failed Loading 'runtimes/win-x64/native/vulkan/llama.dll' > Info: Successfully loaded './runtimes/win-x64/native/avx512/llama.dll'...