The story’s score and claims

Comments on No. 57 of 95 · GitHub · edition of Tuesday 10 November 2026

Hours of YouTube and 85 handtyped pages of notes on LLM Inference – Start here

Summary

Samir Sarwar has published a self-taught video series and C++17/CUDA project, samir-vllm, that builds a small LLM inference engine for Llama 3.2 1B from scratch. It covers safetensors weight loading, a BPE tokenizer, transformer layers, a paged KV cache, and static or continuous batching, with companion handwritten notes.

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules