Abstract: Selecting appropriate research and development (R&D) projects under budget constraints is a critical yet challenging task for enterprises. During development, these projects are inevitably ...

Autocomp is a portable, extensible framework for LLM-driven kernel optimization across tensor accelerators. Point it at a kernel, pick your hardware target, and Autocomp speeds it up, automatically.

I built this project to understand how Markowitz mean-variance optimization actually works in practice - not just the theory, but what happens when you apply it to real assets with correlated returns.