Writing

Jun 12, 2026

An interactive visual guide to KL divergence: distributions, the formula, live computation, and how it shows up in LLMs and PPO training.

Jan 25, 2026

Step-by-step Excel breakdown of router logits → top-k selection → normalized expert probabilities. Includes top-k masking, −∞ replacement, softmax, and final expert routing weights.

Dec 20, 2025

Automated multi-language documentation sync across feature branches.

Jul 26, 2025

Reducing inference latency using KV cache.

Jul 9, 2025

Effect of temperature on next-token probability distribution.

Jun 25, 2025

How masking enforces autoregressive generation in decoder-only transformers.

Jun 21, 2025

How queries, keys, and values compute attention weights and why it matters.

Jun 3, 2025

How tokenizers are trained and why the vocabulary choice shapes model behavior.