Intel B580 -> not able to run Ollama serve on GPU after following guide

[Mushtaq-BGA]

Intel B580 -> not able to run Ollama serve on GPU after following guide

https://github.com/intel/ipex-llm/blob/main/docs/mddocs/Quickstart/bmg_quickstart.md#32-ollama
https://github.com/intel/ipex-llm/blob/main/docs/mddocs/Quickstart/ollama_quickstart.md

[liu-shaojun]

Hi @Mushtaq-BGA

Based on your screenshot, the output from ollama serve looks normal. Could you share the exact error message you're encountering? Alternatively, you can try running the following commands to see if everything works correctly:

./ollama pull <model_name>
./ollama run <model_name>

Let me know the results!

[Mushtaq-BGA]

[liu-shaojun]

Debugged the issue on the user's machine, and the root cause was that he had oneAPI version 2024.0 installed. After switching to oneAPI 2024.2, it worked normally.