David Noel Ng
ML, Biotech, Hardware, and Coordination Problems. Sometimes I write about hard problems and how to solve them.
- Posts
- 16 from 8 Nov 2025 to 9 Sep 2026
- Posting
- monthly (16 in the last year)
- Kind
- personal blog
- Feed
- https://dnhkng.github.io/feed.xml
2026 13
- Teaching an M4 CPU to Tell Stories with XOR, Popcount and SDOT
- 2x GH200 for LLM inference, Part 4: DeepSeek V4 Flash - SGLang vs vLLM at 1M context
- Building the Beam Universe Splitter II: Building a Quantum LLM
- Building the Beam Universe Splitter I: A Quantum Magic 8-Ball
- 2x GH200 for LLM inference, Part 3: GLM-5.2, expert offload, and the CPU question
- Building & Benchmarking: LLMs on a 16GB Jetson Orin NX for Hermes Agent
- 2x GH200 for LLM inference, Part 2: vLLM, DeepSeek V4 Flash/Pro, and MTP
- What 2x GH200 delivers: memory paths for LLM inference
- LLM Neuroanatomy III: Why RYS Works — The Language-Agnostic Middle
- LLM Neuroanatomy II: Modern LLM Hacking and hints of a Universal Language?
- LLM Neuroanatomy: How I Topped the LLM Leaderboard Without Changing a Single Weight
- Arrhenius Integrals, IR Lasers, and Cooking Proteins
- Optimising a 2× GH200 system for Claude Code