Jesse Gu

Jesse (Zhuangcheng) Gu is a Summer 2026 systems software engineering intern on the Dynamo team focused on multimodal inference serving optimization. He is a master’s student at Carnegie Mellon University, focusing on AI engineering and systems. Previously, he has worked on inference optimization and VLM post-training at Shanghai AI Lab on projects such as MinerU, and has also collaborated with the SGLang RL/multimodal teams on feature development and model support.
Avatar photo

Posts by Jesse Gu

Computer Vision / Video Analytics Sep 09, 2026

When to Use Encode-Prefill-Decode Disaggregation to Accelerate Multimodal Model Serving

Encode-prefill-decode (EPD) disaggregation is an inference optimization technique for multimodal models that separates the vision encoder stage from the prefill... 14 MIN READ