The Closing of the Recipe
Part 5. When every model shares one skeleton, the moat becomes the thing nobody publishes.
I received my PhD from the ECSE Department at Rensselaer Polytechnic Institute, where I was advised by Tong Zhang.
Before that, I earned my BE from Southern University of Science and Technology.
My research focuses on memory architecture and computer systems, with a particular interest in DRAM and SSDs. I work on improving performance and efficiency for data processing and AI infrastructure.
Recent Posts
The Death of Chinchilla
Part 4. Why the most cited recipe in pretraining optimizes the wrong thing, and why emergence is mostly a measurement artifact.
Logical KV Savings Are Not Physical Memory Savings
Token-level KV cache eviction can report large logical savings while returning little usable GPU memory to a paged allocator. How much it actually returns is...
Why a Busy GPU Is Not a Useful GPU in LLM Serving
A reproducible mechanism study of schedulability, KV-cache lifecycle, and useful tokens per dollar in LLM serving, with a controlled scheduler ablation and h...
Pretraining Is a Fab Problem
Part 3. Why the frontier is gated by memory bandwidth, packaging capacity, and depreciation, and barely at all by ideas about intelligence.