corpus.blog
54,302 blogs · [ { "id": "01a08c95-fae6-733b-b354-2d51bbe12ebf", "title": "Teaching an M4 CPU to Tell Stories with XOR, Popcount and SDOT", "url": "https://dnhkng.github.io/posts/m4-tinystories/", "published_at": "2026-09-09T22:00:00+00:00" }, { "id": "01a0876e-301c-71ea-966c-d19951ad5830", "title": "2x GH200 for LLM inference, Part 4: DeepSeek V4 Flash - SGLang vs vLLM at 1M context", "url": "https://dnhkng.github.io/posts/gh200-benchmarking-part-4-dsv4-released/", "published_at": "2026-08-03T22:00:00+00:00" }, { "id": "01a0876e-301c-71ea-966c-d19951c52c96", "title": "Building the Beam Universe Splitter II: Building a Quantum LLM", "url": "https://dnhkng.github.io/posts/building-a-quantum-llm/", "published_at": "2026-07-21T22:00:00+00:00" }, { "id": "01a0876e-301c-71ea-966c-d19952998007", "title": "Building the Beam Universe Splitter I: A Quantum Magic 8-Ball", "url": "https://dnhkng.github.io/posts/building-the-beam-universe-splitter/", "published_at": "2026-06-24T22:00:00+00:00" }, { "id": "01a0876e-301c-71ea-966c-d1995366d008", "title": "2x GH200 for LLM inference, Part 3: GLM-5.2, expert offload, and the CPU question", "url": "https://dnhkng.github.io/posts/gh200-benchmarking-part-3-glm52/", "published_at": "2026-06-16T22:00:00+00:00" }, { "id": "01a0876e-301c-71ea-966c-d19953e71559", "title": "Building & Benchmarking: LLMs on a 16GB Jetson Orin NX for Hermes Agent", "url": "https://dnhkng.github.io/posts/jetson-orin-nx-vram-tuning/", "published_at": "2026-06-08T22:00:00+00:00" } ] posts Claim your blog
Back to dnhkng.github.io
Blog · corpus.blog/blogs/dnhkng.github.io/posts

dnhkng.github.io

dnhkng.github.io

2026

Teaching an M4 CPU to Tell Stories with XOR, Popcount and SDOToriginal ↗
9 Sept 2026
2x GH200 for LLM inference, Part 4: DeepSeek V4 Flash - SGLang vs vLLM at 1M contextoriginal ↗
3 Aug 2026
Building the Beam Universe Splitter II: Building a Quantum LLMoriginal ↗
21 Jul 2026
Building the Beam Universe Splitter I: A Quantum Magic 8-Balloriginal ↗
24 Jun 2026
2x GH200 for LLM inference, Part 3: GLM-5.2, expert offload, and the CPU questionoriginal ↗
16 Jun 2026
Building & Benchmarking: LLMs on a 16GB Jetson Orin NX for Hermes Agentoriginal ↗
8 Jun 2026