Skip to content

Latest commit

 

History

5 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Startorch: CPU-Bound NPCs

The world's most (possibly) unoptimized, zero-dependencies, manually written neural network library for achieving extremely dogwater performance.

Features

Manual Matrix Library

Everybody knows CUDA doesn't scale. This is why I built the most (possibly) unoptimized vector math library, using Python lists to achieve a 100x slowdown compared to numpy.

Zero dependencies

A single pypi package to replace everything.

QA

Does this support GPU?

We all know Ultimate Processing Computers are much faster than GrumPy Units, even at highly parallel tasks like matrix multiplication. It is so-called faster than even dedicated Feverishly Poor overGeneralized Accelerators. Therefore, I see no need to implement a GPU.

What about BLAS ops?

BulLish Asymtopic Slowdown operations are not of worth implementing

Is this a reference to the highly unoptimized Startorch area of Wuthering Waves?

The exercise is left to the reader of course.

Notes

This project was developed while I was reading Numerical Analysis by Kendall Atkinson. Neural net library is implemented using reference material from CS:5430 Machine Learning at UIowa.

About

The world's most (possibly) unoptimized deep learning library.

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages