jetyolo
JetYOLO:Speed through your TensorRT/Deepstream app development.
On-chain. AI-native. Inevitable. Founder @qntx
JetYOLO:Speed through your TensorRT/Deepstream app development.
Llama from scratch in Go.
A lightweight, high-performance deep learning inference tool.
Llama from scratch in CUDA with Flash Attention.
Flash Attention: Theory → Code → Optimization
A simple bitcoin implementation in Rust.
Sudoku in Rust, Python and WASM.
Llama from scratch in Rust.
A simple STARK implementation in Go.
Unofficial source-oriented reconstruction and extension of Grok Bot 0.18.0 for macOS
A simple EVM implementation in Rust.