spikedoanz / from-bits-to-intelligenceLinks
could we make an ml stack in 100,000 lines of code?
☆46Updated last year
Alternatives and similar repositories for from-bits-to-intelligence
Users that are interested in from-bits-to-intelligence are comparing it to the libraries listed below
Sorting:
- parallelized hyperdimensional tictactoe☆118Updated 11 months ago
- Solve puzzles to improve your tinygrad skills!☆140Updated 4 months ago
- Tutorials on tinygrad☆396Updated last month
- Following master Karpathy with GPT-2 implementation and training, writing lots of comments cause I have memory of a goldfish☆172Updated last year
- Simple Transformer in Jax☆138Updated last year
- Gradient descent is cool and all, but what if we could delete it?☆104Updated last week
- Tensor library with autograd using only Rust's standard library☆68Updated last year
- small auto-grad engine inspired from Karpathy's micrograd and PyTorch☆274Updated 8 months ago
- ☆87Updated last week
- ☆96Updated last year
- in this repository, i'm going to implement increasingly complex llm inference optimizations☆64Updated 2 months ago
- This repo is my attempt at a rough implementation of nanoGPT trained on a dataset of 30,000 unique Twitter usernames☆24Updated last year
- A really tiny autograd engine☆95Updated 2 months ago
- Ultra low overhead NVIDIA GPU telemetry plugin for telegraf with memory temperature readings.☆62Updated last year
- SIMD quantization kernels☆76Updated last week
- High Quality Resources on GPU Programming/Architecture☆588Updated last year
- An implement of deep learning framework and models in C☆48Updated 4 months ago
- a tiny multidimensional array implementation in C similar to numpy, but only one file.☆228Updated last year
- i will automate factorio☆108Updated last year
- An implementation of delta-iris in tinygrad☆72Updated 11 months ago
- Compiling useful links, papers, benchmarks, ideas, etc.☆45Updated 4 months ago
- moondream in zig.☆73Updated 2 months ago
- Learning about CUDA by writing PTX code.☆133Updated last year
- ☆92Updated 6 months ago
- speedrun implementation of dl papers throughout history☆33Updated last year
- Alex Krizhevsky's original code from Google Code☆195Updated 9 years ago
- Just large language models. Hackable, with as little abstraction as possible. Done for my own purposes, feel free to rip.☆44Updated last year
- a tiny vectorstore implementation built with numpy.☆62Updated last year
- The Tensor (or Array)☆441Updated 11 months ago
- pytorch from scratch in pure C/CUDA and python☆40Updated 9 months ago