GPU

BigDL-LLM Examples on Intel GPU

This folder contains examples of running BigDL-LLM on Intel GPU:

• HF-Transformers-AutoModels: running any Hugging Face Transformers model on BigDL-LLM (using the standard AutoModel APIs)
• PyTorch-Models: running any PyTorch model on BigDL-LLM (with "one-line code change")
• QLoRA-FineTuning: running QLoRA finetuning on BigDL-LLM

System Support

Hardware:

• Intel Arc™ A-Series Graphics
• Intel Data Center GPU Flex Series
• Intel Data Center GPU Max Series

Operating System:

• Ubuntu 20.04 or later (Ubuntu 22.04 is preferred)

Requirements

To apply Intel GPU acceleration, there’re several steps for tools installation and environment preparation.

Step 1, please refer to our driver installation for general purpose GPU capabilities.

Note: IPEX 2.0.110+xpu requires Intel GPU Driver version is Stable 647.21.

Step 2, you also need to download and install Intel® oneAPI Base Toolkit. OneMKL and DPC++ compiler are needed, others are optional.

Note: IPEX 2.0.110+xpu requires Intel® oneAPI Base Toolkit's version >= 2023.2.0.