LlamaIndex Llms Integration: IPEX-LLM

IPEX-LLM is a PyTorch library for running LLM on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max) with very low latency. This module enables the use of LLMs optimized with ipex-llm in LlamaIndex pipelines.

Installation

On CPU

pip install llama-index-llms-ipex-llm

On GPU

pip install llama-index-llms-ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/

Usage

from llama_index.llms.ipex_llm import IpexLLM

Examples

• Notebook Example
• More Examples