Tun Jian Tan

LLM Principal Engineer, Embedded LLM | vLLM Maintainer

Specializing in high-performance LLM inference on AMD GPUs, Tun Jian Tan is an LLM Principal Engineer at Embedded LLM and a maintainer of the open-source vLLM project. As an early contributor to AMD GPU support in vLLM, he has helped advance ROCm integration, inference optimization, and quantization capabilities. His contributions have also been recognized with the AMD AI Contributor Award, reflecting his ongoing work in advancing the open-source AI inference ecosystem.

Abdennacer Badaoui

ML Engineer at Hugging Face

Abdennacer Badaoui is a Machine Learning Engineer at Hugging Face, working at the intersection of open-source AI and hardware optimization. He focuses on bringing open models to AMD GPUs, making them easy to train, fine-tune and run efficiently across the Hugging Face ecosystem.