Hi, I'm SIRU HE, a Master's student in Electronic Information at SUSTech (jointly trained with SIAT-CAS), working on LLM inference and AI infrastructure.
My internship experience sits at the inference-system and kernel layers: at ModelBest I worked on the multimodal inference runtime for MiniCPM-o 4.5 and VoxCPM2, and at Shanghai Guangyu Xinchen I optimized LLM Decode-stage operators and worked on megakernel fusion. I also contribute to open-source projects like RL-Kernel and vLLM-Omni.
I write about these things on the blog. You can reach me at siruhe666@gmail.com.