micrograd
ggez
Our great sponsors
micrograd | ggez | |
---|---|---|
22 | 50 | |
8,273 | 4,111 | |
- | 1.4% | |
0.0 | 4.3 | |
5 days ago | 6 days ago | |
Jupyter Notebook | Rust | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
micrograd
-
Micrograd-CUDA: adapting Karpathy's tiny autodiff engine for GPU acceleration
I recently decided to turbo-teach myself basic cuda with a proper project. I really enjoyed Karpathy’s micrograd (https://github.com/karpathy/micrograd), so I extended it with cuda kernels and 2D tensor logic. It’s a bit longer than the original project, but it’s still very readable for anyone wanting to quickly learn about gpu acceleration in practice.
-
Stuff we figured out about AI in 2023
FOr inference, less than 1KLOC of pure, dependency-free C is enough (if you include the tokenizer and command line parsing)[1]. This was a non-obvious fact for me, in principle, you could run a modern LLM 20 years ago with just 1000 lines of code, assuming you're fine with things potentially taking days to run of course.
Training wouldn't be that much harder, Micrograd[2] is 200LOC of pure Python, 1000 lines would probably be enough for training an (extremely slow) LLM. By "extremely slow", I mean that a training run that normally takes hours could probably take dozens of years, but the results would, in principle, be the same.
If you were writing in C instead of Python and used something like Llama CPP's optimization tricks, you could probably get somewhat acceptable training performance in 2 or 3 KLOC. You'd still be off by one or two orders of magnitude when compared to a GPU cluster, but a lot better than naive, loopy Python.
[1] https://github.com/karpathy/llama2.c
[2] https://github.com/karpathy/micrograd
-
Writing a C compiler in 500 lines of Python
Perhaps they were thinking of https://github.com/karpathy/micrograd
- Linear Algebra for Programmers
- Understanding Automatic Differentiation in 30 lines of Python
-
Newbie question: Is there overloading of Haskell function signature?
I was (for fun) trying to recreate micrograd in Haskell. The ideia is simple:
-
[D] Backpropagation is not just the chain-rule, then what is it?
Check out this repo I found a few years back when I was looking into understanding pytorch better. It's basically a super tiny autodiff library that only works on scalars. The whole repo is under 200 lines of code, so you can pull up pycharm or whatever and step through the code and see how it all comes together. Or... you know. Just read it, it's not super complicated.
-
Neural Networks: Zero to Hero
I'm doing an ML apprenticeship [1] these weeks and Karpathy's videos are part of it. We've been deep down into them. I found them excellent. All concepts he illustrates are crystal clear in his mind (even though they are complicated concepts themselves) and that shows in his explanations.
Also, the way he builds up everything is magnificent. Starting from basic python classes, to derivatives and gradient descent, to micrograd [2] and then from a bigram counting model [3] to makemore [4] and nanoGPT [5]
[1]: https://www.foundersandcoders.com/ml
[2]: https://github.com/karpathy/micrograd
[3]: https://github.com/karpathy/randomfun/blob/master/lectures/m...
[4]: https://github.com/karpathy/makemore
[5]: https://github.com/karpathy/nanoGPT
-
Rustygrad - A tiny Autograd engine inspired by micrograd
Just published my first crate, rustygrad, a Rust implementation of Andrej Karpathy's micrograd!
-
Hey Rustaceans! Got a question? Ask here (10/2023)!
I've been trying to reimplement Karpathy's micrograd library in rust as a fun side project.
ggez
-
ggez news! 0.9.0 released and more!
ggez is a lightweight cross-platform game framework for making games with minimum friction. Check it out at https://github.com/ggez/ggez, https://crates.io/crates/ggez
-
NANOVOID Devlog #1: Lua Scripting
I'd say to use either https://macroquad.rs/ or http://ggez.rs/, they're both basically "all that you need for 2d". I've used macroquad extensively, but that was mainly because ggez was undergoing a big rewrite to wgpu which is now complete with 0.8.
-
Embedding GGEZ into GTK-RS
Hi guys, Is there a guide on how to implement renderers/frameworks such as GGEZ?
- Hey Rustaceans! Got a question? Ask here (12/2023)!
- Hey Rustaceans! Got a question? Ask here (10/2023)!
-
Hey Rustaceans! Got a question? Ask here (9/2023)!
ggez also looks pretty straightforward and simple to get graphics moving around quick and easy.
-
Hey Rustaceans! Got a question? Ask here (8/2023)!
https://github.com/ggez/ggez/issues/1158 For this is it as simple as changing the methods to take &Image, .clone() it inside and use that or is cloning missing the point of the change?
-
Hey Rustaceans! Got a question? Ask here! (51/2022)!
Sounds like https://ggez.rs/.
-
Clean Pixel art in ggez 0.8.1
See the links here on how to do what you want with samplers. https://github.com/ggez/ggez/issues/1046
-
Sokoban clone written in Rust using ggez
Nice, can you add it to the list of projects https://github.com/ggez/ggez/blob/master/docs/Projects.md ?
What are some alternatives?
deepnet - Educational deep learning library in plain Numpy.
bevy - A refreshingly simple data-driven game engine built in Rust
tinygrad - You like pytorch? You like micrograd? You love tinygrad! ❤️ [Moved to: https://github.com/tinygrad/tinygrad]
macroquad - Cross-platform game engine in Rust.
deeplearning-notes - Notes for Deep Learning Specialization Courses led by Andrew Ng.
piston - A modular game engine written in Rust
ML-From-Scratch - Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.
Tetra - 🎮 A simple 2D game framework written in Rust
NNfSiX - Neural Networks from Scratch in various programming languages
Amethyst - Data-oriented and data-driven game engine written in Rust
yolov7 - Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
love - LÖVE is an awesome 2D game framework for Lua.