Blog

  • 28th July 2026

Black-Scholes: an options pricing primer

A concise refresher on the Black-Scholes formula, its assumptions, and how to implement it in Python — with the Greeks.

Read more 
  • 20th July 2026

KV cache: how inference keeps attention fast

Why autoregressive transformers cache keys and values, the memory cost it implies, and the trade-offs in attention computation.

Read more