Tree-based speculative decoding for Apple Silicon. ~10-15% faster than DFlash, ~1.5x faster than autoregressive on Qwen 3.5 27B. DDTree extends DFlash speculative decoding by building a draft tree ...
In its traditional definition, an algorithm means a set of instructions that have been prepared beforehand to solve a particular problem. Algorithms could be an optimum simple procedure or a complex ...
I originally created this as a short to-do list of study topics for becoming a software engineer, but it grew to the large list you see today. After going through this study plan, I got hired as a ...