Pin Siang Tan

Pin Siang Tan is an AI researcher and technical leader with over 14 years of hands-on experience spanning deep learning, generative AI, computer vision, and geospatial analysis. He focuses on pushing the limits of Large Language Model (LLM) inference in production, designing and optimizing systems for high performance, low latency, and massive scalability in real-world environments.

Posts by Pin Siang 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