intel gpu and ollama error

intel-analytics / ipex-llm

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Mixtral, Gemma, Phi, MiniCPM, Qwen-VL, MiniCPM-V, etc.) on Intel XPU (e.g., local PC with iGPU and NPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, vLLM, GraphRAG, DeepSpeed, Axolotl, etc

Apache License 2.0

6.69k stars 1.26k forks source link

intel gpu and ollama error #11217

Open dayskk opened 5 months ago

dayskk commented 5 months ago

微信图片_20240605135354

The following error occurred after running for a period of time, please refer to the attachment. Currently, no reproduction method has been found. GPU accelerates Ollama to run Qwen1.5 7b, and it appears while running

KiwiHana commented 5 months ago

CPU: MTL 135H, windows 11 pro 23H2 Qwen1.5 7b Script: https://ipex-llm.readthedocs.io/en/latest/doc/LLM/Quickstart/ollama_quickstart.html

rnwang04 commented 5 months ago

Hi @dayskk & @KiwiHana , I can't reproduce this issue on our U5 125H.

Maybe double check your GPU memory usage.