Nicolas Oliver

@eaidova we were using this notebook to validate a Meteor Lake system that we later found that it had bad drivers for NPU and GPU. We have validated it in...

This is how a healthy system looks like: - Display Adapters => Intel(R) Arc(TM) Graphics is healthy - Neural Processors => Intel(R) AI Boost is healthy  And this is...

Hi @abetlen! I am experimenting with llama.cpp and llama-cpp-python on my Windows laptop with Intel iGPU. I'm getting a build issue that I can't sort out yet. I can get...

Found the problem. It is caused by LLAVA_BUILD=ON. Disabling it makes it work. To summarize: ```cmd "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force set CMAKE_ARGS="-DLLAVA_BUILD=OFF -DGGML_SYCL=ON -DCMAKE_C_COMPILER=cl -DCMAKE_CXX_COMPILER=icx -DBUILD_SHARED_LIBS=ON" pip install -e...

Yep that works @mschuettlerTN, thanks! Compiled it with your env vars, and I can see the GPU being used, by log and GPU activity.  Still reports `inf` tokens thought...

Reported 3 issues for GPU support: #1851 #1852 #1853