Yineng Zhang
About Me
I’m a Senior Director leading the inference team at Together AI. I also serve on the governing board of the LightSeek Foundation, where I co-created TokenSpeed — a speed-of-light LLM inference engine. My work in AI infrastructure has been recognized through O-1A and EB-1A extraordinary ability classifications in the United States. More about my work and background on my LinkedIn.
Projects
TokenSpeed: TokenSpeed is a speed-of-light LLM inference engine.
Interviews
The New York Times: DeepSeek’s Rise: How a Chinese
Start-Up Went From Stock Trader to A.I. Star:
“Most of the team graduated from the top universities in China,” said Yineng Zhang, a lead software engineer at Baseten in San Francisco who works on the SGLang, a project not part of DeepSeek that helps people build on top of DeepSeek’s system. “They are very smart and very young.”
The New York Times: How Chinese A.I. Start-Up DeepSeek Is
Competing With Silicon Valley Giants:
While employees at big Chinese technology companies are limited to collaborating with colleagues, “if you work on open source, you work with talent around the world,” said Yineng Zhang, lead software engineer at Baseten in San Francisco who works on the open source SGLang project. He helps other people and companies build products using DeepSeek’s system.
Selected Talks
Engineering Real-World LLM Inference: Bridging Open-Source and
Production Systems
Speaker at NVIDIA GTC 2026
Speaker at NVIDIA GTC 2026
Selected Publications
-
Mooncake: A KVCache-centric Disaggregated Architecture for LLM ServingACM Transactions on Storage