https://github.com/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.

---

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 latency¹.

• [2024/03] bigdl-llm has now become ipex-llm (see the migration guide here); you may find the original BigDL project here.
• [2024/02] ipex-llm now supports directly loading model from ModelScope (魔搭).
• [2024/02] ipex-llm added inital INT2 support (based on llama.cpp IQ2 mechanism), which makes it possible to run large-size LLM (e.g., Mixtral-8x7B) on Intel GPU with 16GB VRAM.
• [2024/02] Users can now use ipex-llm through Text-Generation-WebUI GUI.
• [2024/02] ipex-llm now supports Self-Speculative Decoding, which in practice brings ~30% speedup for FP16 and BF16 inference latency on Intel GPU and CPU respectively.
• [2024/02] ipex-llm now supports a comprehensive list of LLM finetuning on Intel GPU (including LoRA, QLoRA, DPO, QA-LoRA and ReLoRA).
• [2024/01] Using ipex-llm QLoRA, we managed to finetune LLaMA2-7B in 21 minutes and LLaMA2-70B in 3.14 hours on 8 Intel Max 1550 GPU for Standford-Alpaca (see the blog here).

More updates

• [2023/12] ipex-llm now supports ReLoRA (see "ReLoRA: High-Rank Training Through Low-Rank Updates").
• [2023/12] ipex-llm now supports Mixtral-8x7B on both Intel GPU and CPU.
• [2023/12] ipex-llm now supports QA-LoRA (see "QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models").
• [2023/12] ipex-llm now supports FP8 and FP4 inference on Intel GPU.
• [2023/11] Initial support for directly loading GGUF, AWQ and GPTQ models into ipex-llm is available.
• [2023/11] ipex-llm now supports vLLM continuous batching on both Intel GPU and CPU.
• [2023/10] ipex-llm now supports QLoRA finetuning on both Intel GPU and CPU.
• [2023/10] ipex-llm now supports FastChat serving on on both Intel CPU and GPU.
• [2023/09] ipex-llm now supports Intel GPU (including iGPU, Arc, Flex and MAX).
• [2023/09] ipex-llm tutorial is released.

See the optimized performance of chatglm2-6b and llama-2-13b-chat models on 12th Gen Intel Core CPU and Intel Arc GPU below.

12th Gen Intel Core CPU		Intel Arc GPU
chatglm2-6b	llama-2-13b-chat	chatglm2-6b	llama-2-13b-chat

• Windows GPU: installing ipex-llm on Windows with Intel GPU
• Linux GPU: installing ipex-llm on Linux with Intel GPU
• Docker: using ipex-llm dockers on Intel CPU and GPU
• For more details, please refer to the installation guide

• llama.cpp: running ipex-llm for llama.cpp (using C++ interface of ipex-llm as an accelerated backend for llama.cpp on Intel GPU)
• vLLM: running ipex-llm in vLLM on both Intel GPU and CPU
• FastChat: running ipex-llm in FastChat serving on on both Intel GPU and CPU
• LangChain-Chatchat RAG: running ipex-llm in LangChain-Chatchat (Knowledge Base QA using RAG pipeline)
• Text-Generation-WebUI: running ipex-llm in oobabooga WebUI
• Benchmarking: running (latency and throughput) benchmarks for ipex-llm on Intel CPU and GPU

• Low bit inference
  • INT4 inference: INT4 LLM inference on Intel GPU and CPU
  • FP8/FP4 inference: FP8 and FP4 LLM inference on Intel GPU
  • INT8 inference: INT8 LLM inference on Intel GPU and CPU
  • INT2 inference: INT2 LLM inference (based on llama.cpp IQ2 mechanism) on Intel GPU
• FP16/BF16 inference
  • FP16 LLM inference on Intel GPU, with possible self-speculative decoding optimization
  • BF16 LLM inference on Intel CPU, with possible self-speculative decoding optimization
• Save and load
  • Low-bit models: saving and loading ipex-llm low-bit models
  • GGUF: directly loading GGUF models into ipex-llm
  • AWQ: directly loading AWQ models into ipex-llm
  • GPTQ: directly loading GPTQ models into ipex-llm
• Finetuning
  • LLM finetuning on Intel GPU, including LoRA, QLoRA, DPO, QA-LoRA and ReLoRA
  • QLoRA finetuning on Intel CPU
• Integration with community libraries
  • HuggingFace tansformers
  • Standard PyTorch model
  • DeepSpeed-AutoTP
  • HuggingFace PEFT
  • HuggingFace TRL
  • LangChain
  • LlamaIndex
  • AutoGen
  • ModeScope
• Tutorials

For more details, please refer to the ipex-llm document website.

Over 50 models have been optimized/verified on ipex-llm, including LLaMA/LLaMA2, Mistral, Mixtral, Gemma, LLaVA, Whisper, ChatGLM2/ChatGLM3, Baichuan/Baichuan2, Qwen/Qwen-1.5, InternLM and more; see the list below.

Model	CPU Example	GPU Example
LLaMA (such as Vicuna, Guanaco, Koala, Baize, WizardLM, etc.)	link1, link2	link
LLaMA 2	link1, link2	link
ChatGLM	link
ChatGLM2	link	link
ChatGLM3	link	link
Mistral	link	link
Mixtral	link	link
Falcon	link	link
MPT	link	link
Dolly-v1	link	link
Dolly-v2	link	link
Replit Code	link	link
RedPajama	link1, link2
Phoenix	link1, link2
StarCoder	link1, link2	link
Baichuan	link	link
Baichuan2	link	link
InternLM	link	link
Qwen	link	link
Qwen1.5	link	link
Qwen-VL	link	link
Aquila	link	link
Aquila2	link	link
MOSS	link
Whisper	link	link
Phi-1_5	link	link
Flan-t5	link	link
LLaVA	link	link
CodeLlama	link	link
Skywork	link
InternLM-XComposer	link
WizardCoder-Python	link
CodeShell	link
Fuyu	link
Distil-Whisper	link	link
Yi	link	link
BlueLM	link	link
Mamba	link	link
SOLAR	link	link
Phixtral	link	link
InternLM2	link	link
RWKV4		link
RWKV5		link
Bark	link	link
SpeechT5		link
DeepSeek-MoE	link
Ziya-Coding-34B-v1.0	link
Phi-2	link	link
Yuan2	link	link
Gemma	link	link
DeciLM-7B	link	link
Deepseek	link	link
StableLM	link	link

Footnotes

1. Performance varies by use, configuration and other factors. ipex-llm may not optimize to the same degree for non-Intel products. Learn more at www.Intel.com/PerformanceIndex. ↩