Di Tian

Di Tian is an MTS Software Development Engineer within AMD’s AI Group, specializing in performance optimization for distributed AI systems—particularly communication stacks and LLM frameworks. His current focus is architecting next-generation communication infrastructure to accelerate both training and inference of large language models at scale.

Posts by Di Tian

Practical, Fault‑Robust Distributed Inference for DeepSeek on AMD MI300X

Learn how a small-radius expert parallel design with prefill–decode disaggregation enables scalable, fault-isolated LLM inference on AMD Instinct™ MI300X clusters.

November 12, 2025 by Peng Sun, Andy Luo, Gilbert Lei, Lingpeng Jin, Carlus Huang, Duyi Wang, Mingzhi Liu, Di Tian, Bill He, Jun Chen, Yutong Wu, Jiahao Zhou, Niko Ma