Alan Wu comments

Results 22 comments of


                                            Alan Wu

ollama ipex-llm crashes when running tinyllama llama 3.1b and qwen 2.5

Hey man I used to get this error before, so I think I can do sth to help. Btw can you send me your error logs?

ollama ipex-llm crashes when running tinyllama llama 3.1b and qwen 2.5

I think it's caused by AMD cpu, they only support intel cpu (I mentioned it to the intel team before). Also `msg="no compatible GPUs were discovered"` is not relevant, just...

ollama ipex-llm crashes when running tinyllama llama 3.1b and qwen 2.5

I talked to the intel team, amd cpu should work. This log is confused, and if you can send me a readable log, which saved by ollama directly but not...

ollama-ipex fails running any models - A380 - llama runner process terminated

As I know, this intel team doesn't release ollama-xeon version, so your model cannot load on xeon cpu. Btw it's a good idea to raise an issue to ask them...

Ollama run crashes using `ipex-llm-inference-cpp-xpu` docker image - A750 - Seg Fault

The reason is that your CPU is too old (i7-6950) — ipex-llm ollama only supports 13th Gen CPUs and newer.

Ollama offload to the CPU then crash

Hi I am also a Linux user. I think it's not due to offloading to cpu, but your sycl config error. Maybe you can activate oneapi and run `sycl-ls` to...

Ollama offload to the CPU then crash

This intel team has released a new linux portable zip release, give it a try to see if that works for you man.

Hope to continue updating for Ollama.

https://github.com/intel/ipex-llm/issues/13308#issuecomment-3319233504

Abnormalities in using Intel GPU SYCL on the Ubuntu system

Check your driver bro

OLLAMA_MAX_LOADED_MODELS Invalid

just unset OLLAMA_MAX_LOADED_MODELS bro lol