SONG Ge
SONG Ge
That's a normal behaviour. You will not see any intel gpu info until you loading a model.
Hi @js333031 , ipex-llm ollama is a GPU-optimized version, so we currently do not plan to work on this.
Hi @JerryXu2023, we have reproduced your issue and are currently working on a fix. As a temporary workaround, you may install version 20240911.
Hi @bmh129 , we are working on adding support for `gemma3` model, and it will be released next week. Pls stay tuned ：）
You may install the latest version of ollama and init ollama again with commands below: ```bash pip install --pre --upgrade ipex-llm[cpp] init-ollama.bat ``` https://github.com/intel-analytics/ipex-llm/blob/main/docs/mddocs/Quickstart/ollama_quickstart.md
We have reproduced your issue and will respond with a solution as soon as possible.