articles and knowledge

Three focused engineering books from ChatVariety Team for teams running AI in production — fast LLM serving with vLLM, quantization and speculative decoding, reliable GPU cluster operations, and AI unit economics — with a recommended reading order and Kindle and paperback links.

Four ChatVariety Team books on Amazon – Semiconductor Engineering History, Pre-Training LLM Engineering, AI Cost Management and Quantum Computing Engineering – compared side by side, with a reading order and a link for every book.

A practical guide from the Scaling AI Systems Series for teams whose AI bills are growing faster than their revenue: GPU spend, LLM token costs and the unit economics that decide whether an AI product makes money. On Kindle and in paperback.

An engineering guide from the Production AI Engineering Series covering the three pillars of building a large language model from scratch: distributed training, architecture design and scaling laws. On Kindle and in paperback.

A 92-page engineering playbook for running LLM applications in production — observability with Langfuse and Arize, evaluation with DeepEval and RAGAS, RAG architecture, cost optimisation and safe rollouts. Here's what's inside, who it's for, and where to read it on Google Play Books.