Giters

intel-analytics / ipex-llm

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

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

all-in-one with version 2.1.0b1 failed

Fred-cell opened this issue · comments

commented

benchmark llama-3-8b failed:
image

commented

Will try to reproduce from our side

commented

Hi @Fred-cell, I followed the steps below, cannot reproduce this issue from our side

conda create -n llm python=3.10
conda activate llm
pip install --pre --upgrade ipex-llm[xpu]==2.1.0b1 --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/

pip install transformers==4.37.0
pip install omegaconf
pip install pandas
bash run-arc.sh

Can you provide the env information using https://github.com/intel-analytics/ipex-llm/blob/main/python/llm/scripts/env-check.sh?

commented

According to the offline synchronization with @Fred-cell , the cause of the problem was that oneapi 2024.1 was installed in their environment. We recommended that they install oneapi 2024.0 according to the guide and the problem was solved.