naklecha/simple-llm

~1300 line, minimal, extensible LLM inference engine built from scratch.

3 best points · 0 comments · 1 Hacker News post · 492 GitHub stars · View on GitHub

Hacker News discussions

• Snow HN: ~950 line inference engine, on par with vLLM (3 points, 0 comments, by naklecha, 2026-01-08)