farukalpay/stories100m

This repository contains the reference implementation for the paper "Bare-Metal Tensor Virtualization: Overcoming the Memory Wall in Edge-AI Inference".

8 best points · 0 comments · 2 Hacker News posts · 7 GitHub stars · View on GitHub

Hacker News discussions

• Llama 2 inference from scratch in C++20 (No PyTorch/GGML, ARM NEON) (8 points, 0 comments, by recoverydial, 2026-01-06)
• Bare-Metal Llama 2 Inference in C++20 (No Frameworks, ARM Neon) (3 points, 0 comments, by ornurla, 2026-01-08)