tinygrad / teenygrad
If tinygrad wasn't small enough for you...
☆632Updated 6 months ago
Related projects: ⓘ
- Tutorials on tinygrad☆157Updated 2 weeks ago
- The Tensor (or Array)☆388Updated last month
- commaVQ is a dataset of compressed driving video☆289Updated 2 months ago
- Some ipython notebooks implementing AI algorithms☆1,247Updated last month
- The Autograd Engine☆482Updated last week
- Puzzles for learning Triton☆966Updated last week
- Letting computers listen to you and really care☆365Updated 2 years ago
- Tile primitives for speedy kernels☆1,489Updated this week
- ctypes wrappers for HIP, CUDA, and OpenCL☆122Updated 2 months ago
- The comma.ai Calibration Challenge!☆973Updated 6 months ago
- The Multilayer Perceptron Language Model☆504Updated last month
- UNet diffusion model in pure CUDA☆562Updated 2 months ago
- High Quality Resources on GPU Programming/Architecture☆561Updated last month
- Alex Krizhevsky's original code from Google Code☆185Updated 8 years ago
- ☆97Updated 3 weeks ago
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,214Updated 10 months ago
- parallelized hyperdimensional tictactoe☆105Updated 3 weeks ago
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,639Updated last week
- What would you do with 1000 H100s...☆816Updated 8 months ago
- CUDA related news and material links☆1,079Updated 2 weeks ago
- Deep learning for dummies. All the practical details and useful utilities that go into working with real models.☆665Updated last month
- The n-gram Language Model☆1,294Updated last month
- Scripts and environment for the tinybox☆92Updated 4 months ago
- Open weights language model from Google DeepMind, based on Griffin.☆595Updated 2 months ago
- A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.☆452Updated last week
- ☆373Updated 2 months ago
- Implementation of Diffusion Transformer (DiT) in JAX☆246Updated 3 months ago
- Puzzles for exploring transformers☆293Updated last year
- Make PyTorch models up to 40% faster! Thunder is a source to source compiler for PyTorch. It enables using different hardware executors a…☆1,135Updated this week
- Pure Python from-scratch zero-dependency implementation of Bitcoin for educational purposes☆1,567Updated 3 years ago