Chang Liu

Chang Liu is an SMTS Product Application Engineer in the Artificial Intelligence group at AMD, where she is responsible for exploring features that accelerate LLM serving on AMD GPUs. She holds a Master’s degree in Advanced Computer Science from University of Cambridge. Her interest lies in enabling various AI applications, including LLMs and computer vision, to run efficiently and robustly.

Posts by Chang Liu

Efficient LLM Serving with MTP: DeepSeek V3 and SGLang on AMD Instinct GPUs

This blog will show you how to speed up LLM inference with Multi-Token Prediction in DeepSeek V3 & SGLang on AMD Instinct GPUs

September 11, 2025 by Chang Liu, Andy Luo, Anshul Gupta

Speculative Decoding - Deep Dive

This blog shows the performance improvement achieved by applying speculative decoding with Llama models on AMD MI300X GPUs, tested across models, input sizes, and datasets.

March 24, 2025 by Chang Liu