Tun Jian Tan

Tun Jian Tan is an AI researcher and engineer with 7+ years of experience spanning deep learning, computer vision, and autonomous systems. He previously engineered software for LiDAR point cloud analysis and autonomous robot motion control. Currently, he focuses on pushing the limits of Generative AI and ML Systems, particularly for Large Language Model (LLM) inference on AMD platforms. As a committer and core contributor to vLLM, he works on critical optimizations and ensures robust compatibility to bring high-performance inference to AMD hardware.

Posts by Tun Jian Tan

Accelerated LLM Inference on AMD Instinct™ GPUs with vLLM 0.9.x and ROCm

vLLM v0.9.x is here with major ROCm™ optimizations—boosting LLM performance, reducing latency, and expanding model support on AMD Instinct™ GPUs.

June 28, 2025 by Hongxia Yang, Peng Sun, Tun Jian Tan, Pin Siang Tan, Anshul Gupta