RuntimeError: Unable to run model on ipex-llm[cpp] using intel 1240p

[1009058470]

硬件环境
cpu：Intel i5-1240p / AMD
gpu：Intel Iris Xe / AMD Radeon
内存：16GB DDR4
os：Windows 11
重现步骤
I read this doc try to run ollama on my machiche
and also set this

setx OLLAMA_DEBUG 1
ollama serve 2 > debug.log
ollama run deepseek-r1:7b

I also try deepseek-r1:1.5b and llama3.2:1b

then error showed
debug.txt
OS
Windows

GPU
Intel

CPU
Intel

Ollama version
ollama version is 0.5.1-ipexllm-20250123 Warning: client version is 0.5.7

but when i try to set this value in (doc)[https://github.com/intel/ipex-llm/blob/main/docs/mddocs/Quickstart/ollama_quickstart.md#8-save-gpu-memory-by-specify-ollama_num_parallel1]
set OLLAMA_NUM_PARALLEL=1 that will can run the model, but when i try to say to it's, it will broken down

try_to_say_to_model_debug.txt

[sgwhat]

Hi @1009058470, how did you pull deepseek-r1:7b and llama3.2:1b? We recommend that you download the model by using the ollama pull command.

[1009058470]

Hi @1009058470, how did you pull deepseek-r1:7b and llama3.2:1b? We recommend that you download the model by using the ollama pull command.

ollama run deepseek-r1:7b
and then talk with it in cmd

[sgwhat]

Hi @1009058470 , I am not able to reproduce your issue. And we have released a new version of ipex-llm ollama, you may install it in a new conda env via pip install --pre --upgrade ipex-llm[cpp] to see if it works.

[1009058470]

Hi @1009058470 , I am not able to reproduce your issue. And we have released a new version of ipex-llm ollama, you may install it in a new conda env via pip install --pre --upgrade ipex-llm[cpp] to see if it works.

emmm I have run that ,but seem it do not run on gpu but only cpu

[sgwhat]

Could you pls provide the detailed ollama server log?