Jason Dai

icon indicating a website link https://www.linkedin.com/in/jasondai/ icon indicating an email [email protected]

icon company Intel icon location Intel Fellow; creator of IPEX-LLM, BigDL and Analytics Zoo; committer and PMC member of Apache Spark; mentor of Apache MXNet

Results 106 comments of Jason Dai

Support for gemma3 from google

> Tried `ollama-ipex-llm-2.2.0b20250318-ubuntu.tgz`, I got: > > ``` > ❯ ./ollama run gemma3:4b > Error: llama runner process has terminated: error loading model: error loading model hyperparameters: key not found...

Support for gemma3 from google

> > while the image input support is still WIP > > Yesterday I tried to run it directly through lama-сpp - and it worked (on 2-3x A770). > >...

undefined symbol: iJIT_NotifyEvent with oneapi 2024.2, but no issue with 2024.0.1

> > Hi @Jianshui Based on our offline sync, we currently recommend using oneAPI 2024.0.1 If we upgrade to 2024.2 in the future, we will update you accordingly. > >...

Quantized model loading method expects the model should be locally available.

Do you have an example huggingface hub link that we can test?

Error running llama.cpp with IPEX-LLM on MTL iGPU following quickstart guide (Native API returns: -30 (PI_ERROR_INVALID_VALUE))

Please run the ENV-Check script in https://github.com/intel-analytics/ipex-llm/tree/main/python/llm/scripts

Cannot find dGPU when install ollama on Windows

> > To run ipex-llm ollama on your dGPU, you only need to install ipex-llm[cpp] > > Is there documentation that explains these options? What does installing ipex-llm[xpu] do that...