This folder contains examples of running IPEX-LLM on Intel CPU:
- HF-Transformers-AutoModels: running any Hugging Face Transformers model on IPEX-LLM (using the standard AutoModel APIs)
- QLoRA-FineTuning: running QLoRA finetuning using IPEX-LLM on intel CPUs
- vLLM-Serving: running vLLM serving framework on intel CPUs (with IPEX-LLM low-bit optimized models)
- Deepspeed-AutoTP: running distributed inference using DeepSpeed AutoTP (with IPEX-LLM low-bit optimized models)
- LangChain: running LangChain applications on IPEX-LLM
- Applications: running LLM applications (such as agent, streaming-llm) on BigDl-LLM
- PyTorch-Models: running any PyTorch model on IPEX-LLM (with "one-line code change")
- Native-Models: converting & running LLM in
llama/chatglm/bloom/gptneox/starcodermodel family using native (cpp) implementation - Speculative-Decoding: running any Hugging Face Transformers model with self-speculative decoding on Intel CPUs
- ModelScope-Models: running ModelScope model with IPEX-LLM on Intel CPUs
Hardware:
- Intel® Core™ processors
- Intel® Xeon® processors
Operating System:
- Ubuntu 20.04 or later (glibc>=2.17)
- CentOS 7 or later (glibc>=2.17)
- Windows 10/11, with or without WSL
For better performance, it is recommended to set environment variables on Linux with the help of IPEX-LLM:
pip install --pre --upgrade ipex-llm[all] --extra-index-url https://download.pytorch.org/whl/cpu
source ipex-llm-init