tinygrad / teenygrad
If tinygrad wasn't small enough for you...
☆706Updated last year
Alternatives and similar repositories for teenygrad:
Users that are interested in teenygrad are comparing it to the libraries listed below
- Tutorials on tinygrad☆359Updated last week
- The Tensor (or Array)☆427Updated 7 months ago
- Solve puzzles to improve your tinygrad skills!☆121Updated 3 weeks ago
- The Autograd Engine☆588Updated 6 months ago
- Some ipython notebooks implementing AI algorithms☆1,319Updated 5 months ago
- commaVQ is a dataset of compressed driving video☆301Updated 3 weeks ago
- Can you design a controller to steer a simulated car?☆222Updated 2 months ago
- Scripts and environment for the tinybox☆93Updated 11 months ago
- Letting computers listen to you and really care☆369Updated 2 years ago
- High Quality Resources on GPU Programming/Architecture☆584Updated 8 months ago
- The Multilayer Perceptron Language Model☆545Updated 7 months ago
- ctypes wrappers for HIP, CUDA, and OpenCL☆129Updated 9 months ago
- UNet diffusion model in pure CUDA☆600Updated 9 months ago
- Reproducing Yann LeCun 1989 paper "Backpropagation Applied to Handwritten Zip Code Recognition", to my knowledge the earliest real-world …☆628Updated last year
- ☆79Updated this week
- The n-gram Language Model☆1,408Updated 7 months ago
- tiny corporation website☆6Updated last week
- ☆440Updated 2 weeks ago
- Alex Krizhevsky's original code from Google Code☆191Updated 9 years ago
- The comma.ai Calibration Challenge!☆973Updated last year
- port of Andrjey Karpathy's llm.c to Mojo☆352Updated 3 months ago
- Simple Byte pair Encoding mechanism used for tokenization process . written purely in C☆129Updated 4 months ago
- parallelized hyperdimensional tictactoe☆118Updated 7 months ago
- Puzzles for exploring transformers☆335Updated last year
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆342Updated 8 months ago
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,748Updated 3 months ago
- Multi-Threaded FP32 Matrix Multiplication on x86 CPUs☆343Updated last month
- Gradient descent is cool and all, but what if we could delete it?☆103Updated this week
- An autoregressive character-level language model for making more things☆2,975Updated 9 months ago
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,252Updated 3 months ago