Archives
- 25 Jun Building the
BeamUniverse Splitter I: A Quantum Magic 8-Ball - 17 Jun 2x GH200 for LLM inference, Part 3: GLM-5.2, expert offload, and the CPU question
- 09 Jun Building & Benchmarking: LLMs on a 16GB Jetson Orin NX for Hermes Agent
- 08 Jun 2x GH200 for LLM inference, Part 2: vLLM, DeepSeek V4 Flash/Pro, and MTP
- 25 Apr What 2x GH200 delivers: memory paths for LLM inference
- 26 Mar LLM Neuroanatomy III: Why RYS Works — The Language-Agnostic Middle
- 22 Mar LLM Neuroanatomy II: Modern LLM Hacking and hints of a Universal Language?
- 10 Mar LLM Neuroanatomy: How I Topped the LLM Leaderboard Without Changing a Single Weight
- 25 Feb Arrhenius Integrals, IR Lasers, and Cooking Proteins
- 11 Jan Optimising a 2× GH200 system for Claude Code