autograd
pytorch-book
PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch:入门与实战》)
- 13k
- Jupyter Notebook
- MIT
- 3 y ago
interviews.ai
It is my belief that you, the postgraduate students and job-seekers for whom the book is primarily meant will benefit from reading it; however, it is my hope that even the most experienced researchers will find it fascinating as well.
- 4.9k
- 2 d ago
pennylane
PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.
- 3.5k
- Python
- Apache-2.0
- 1 d ago
Arraymancer
A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices via OpenMP, Cuda and OpenCL backends
- 1.4k
- Nim
- Apache-2.0
- 3 wk ago
pytorch_sparse
PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations
- 1.1k
- Python
- MIT
- 6 mo ago
demos
Introductions to key concepts in quantum programming, as well as tutorials and implementations from cutting-edge quantum computing research.
- 679
- Python
- Apache-2.0
- 3 d ago
AutoGrad-Engine
A complete GPT language model (training and inference) in ~600 lines of pure C#, zero dependencies
- 403
- C#
- MIT
- 4 wk ago
ml-by-hand
A deep learning library built from scratch with complex neural networks examples built on top for learning purposes.
- 110
- Python
- MIT
- 5 mo ago
tensai
A tiny neural-network framework in pure Go with AVX2 SIMD kernels (GOEXPERIMENT=simd)
- 120
- Go
- MIT
- 2 wk ago
DL4S
Accelerated tensor operations and dynamic neural networks based on reverse mode automatic differentiation for every device that can run Swift - from watchOS to Linux
- 109
- Swift
- MIT
- 6 wk ago
Qualia2.0
Qualia is a deep learning framework deeply integrated with automatic differentiation and dynamic graphing with CUDA acceleration. Qualia was built from scratch.
- 48
- Python
- MIT
- 6 y ago
micro-gpt-and-beyond
Build a GPT from scratch, one concept at a time, from pure Python to PyTorch, JAX, MLX, and production serving. Inspired by Andrej Karpathy's microGPT.
- 47
- Python
- MIT
- 3 mo ago
construire-un-llm-de-zero
Construire un LLM de zéro, à la main et en français : les notebooks des 22 chapitres, des tenseurs jusqu'aux agents IA. Le livre et ses visualisations interactives : llmdezero.com
- 47
- Jupyter Notebook
- Apache-2.0
- 5 mo ago
microGRPO
🐭 A tiny single-file implementation of Group Relative Policy Optimization (GRPO) as introduced by the DeepSeekMath paper
- 46
- Python
- MIT
- 17 mo ago
micrograd.c
Port of Karpathy's micrograd in pure C. Micrograd is a tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API.
- 37
- C
- 2 y ago
flint
A toy deep learning framework implemented in pure Numpy from scratch. Aka homemade PyTorch lol.
- 32
- Python
- MIT
- 5 y ago
radgrad
Tracing-based reverse mode automatic differentiation (like autograd!)
- 29
- Python
- Unlicense
- 22 mo ago
affon
TypeScript runtime for scientific computing, tensor programs, and machine learning.
- 27
- TypeScript
- MPL-2.0
- 8 h ago










