harshuljain13/llm-inference-at-scale
A Practitioner handbook for production llm serving.
5 best points · 0 comments · 2 Hacker News posts · 274 GitHub stars · View on GitHub
Hacker News discussions
- Why LLM decode is memory-bound, not compute-bound (5 points, 0 comments, by harshuljain13, 2026-05-28)
- Free LLM inference handbook: 100 engineers cloned it in week 1 (2 points, 0 comments, by harshuljain13, 2026-06-06)