commaai / commavqLinks
commaVQ is a dataset of compressed driving video
☆339Updated 2 months ago
Alternatives and similar repositories for commavq
Users that are interested in commavq are comparing it to the libraries listed below
Sorting:
- Can you design a controller to steer a simulated car?☆336Updated 5 months ago
- A gymnasium environment for the comma body☆37Updated 10 months ago
- If tinygrad wasn't small enough for you...☆761Updated last year
- Tutorials on tinygrad☆445Updated 2 months ago
- Scripts and environment for the tinybox☆95Updated last year
- An implementation of delta-iris in tinygrad☆72Updated last year
- 1 million FPS multi-agent driving simulator☆566Updated 3 weeks ago
- Alex Krizhevsky's original code from Google Code☆197Updated 9 years ago
- Solve puzzles to improve your tinygrad skills!☆171Updated 2 months ago
- Implementation of Diffusion Transformer (DiT) in JAX☆300Updated last year
- The comma.ai Calibration Challenge!☆975Updated last year
- ☆97Updated last week
- Puzzles for exploring transformers☆380Updated 2 years ago
- UNet diffusion model in pure CUDA☆658Updated last year
- Can RL solve simple problems?☆54Updated last year
- A reinforcement learning framework based on MLX.☆249Updated 3 weeks ago
- work @ comma.ai☆174Updated last year
- comma body does a loop around the office☆29Updated 2 years ago
- parallelized hyperdimensional tictactoe☆126Updated last year
- ☆314Updated last year
- For optimization algorithm research and development.☆555Updated last week
- Training pipeline for end-to-end self-driving with Comma AI's Openpilot. WIP☆138Updated 3 years ago
- Reproducing Yann LeCun 1989 paper "Backpropagation Applied to Handwritten Zip Code Recognition", to my knowledge the earliest real-world …☆701Updated last year
- Solve puzzles. Learn CUDA.☆64Updated 2 years ago
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆355Updated last year
- An implementation of the transformer architecture onto an Nvidia CUDA kernel☆201Updated 2 years ago
- Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)☆1,299Updated last year
- ctypes wrappers for HIP, CUDA, and OpenCL☆130Updated last year
- Cost aware hyperparameter tuning algorithm☆176Updated last year
- A really tiny autograd engine☆96Updated 7 months ago