Writing · 10 posts
LLMs
- RoPE: The Phase Geometry Behind Long-Context TransformersHow rotating query and key vectors turns absolute position into relative attention
- From Greedy to Nucleus, How LLMs Choose the Next TokenDecoding algorithms and sampling techniques explained
- The Command Line is Learning to TalkA deep dive into Gemini CLI, Claude CLI, and the rise of shell-native AI agents.
- Breaking the Quadratic BarrierAn Engineer's Guide to the Attention Hacks Behind Million-Token LLMs
- Attention Isn't All You Need. You Also Need a Memory BudgetAn Engineer's Guide to GQA and FlashAttention: The Hacks That Tamed the Transformer's Memory Problem
- From Word2Vec to BERT: The Evolution of Language EmbeddingsHow we taught machines to understand not just words, but the meaning behind them
- From Brute Force to Finesse: The Story of Parameter-Efficient Fine-Tuning (PEFT)How we learned to teach billion-parameter titans new tricks without rebuilding their minds
- RAG: Giving LLMs an External BrainFrom keyword search to semantic retrieval, the journey to grounding models in reality
- How MoE Powers Modern LLMsInside the Architecture That Trains Billion-Scale Models Without Breaking the Bank
- Continuous Batching: The Secret Sauce of High-Throughput LLM InferenceWhy batching in real-time matters, and how vLLM uses it to maximize GPU utilization.