Hello! 👋

I’m Yi Liu, a software engineer passionate about deep learning, model optimization (accuracy and speed). I contribute to vLLM and PyTorch, focusing on making LLM inference faster and more efficient.

Recent Focus

  • Optimizing vLLM inference performance on Intel GPUs and Intel Gaudi accelerators
  • Model quantization and compression techniques: INC, AutoRound, LLM-Compressor, vllm-gaudi
  • Sharing debugging experiences and technical insights

Get In Touch

Feel free to connect with me:

About This Site

This website is built with Hugo, a fast and flexible static site generator, and uses the PaperMod theme.