# Untitled

**#AI #LLM**

### IPEX-LLM

- 매우 짧은 지연 시간으로 **인텔 CPU 및 GPU에서 LLM을 실행**하기 위한 PyTorch 라이브러리

- _llama.cpp, Text-Generation-WebUI, HuggingFace transformers, HuggingFace PEFT, LangChain, LlamaIndex, DeepSpeed-AutoTP, vLLM, FastChat, HuggingFace TRL, AutoGen, ModeScope_ 등과 연동 가능

- 50개 이상의 모델이 최적화 및 검증됨(_LLaMA2, Mistral, Mixtral, Gemma, LLaVA, Whisper, ChatGLM, Baichuan, Qwen, RWKV_ 등)

🔗 [https://github.com/intel-analytics/ipex-llm](https://github.com/intel-analytics/ipex-llm)  

[GitHub - intel-analytics/ipex-llm: Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max). A PyTorch LLM library that seamlessly integrates with llama.cpp, HuggingFace, LangChain, LlamaIndex, DeepSpeed, vLLM, FastChat, ModelScope, etc.](https://github.com/intel-analytics/ipex-llm)

For the site tree, see the [root Markdown](https://slashpage.com/ai-newsbits.md).