✳flâneur — a map of the web's best reading
Compiling ML models to C for fun | Max Bernstein
bernsteinbear.com · 8,683 words · saved by 1 readers
We make micrograd fly with a little compiler magic. In this post, we’ll write a ML compiler from scratch.
Compiling ML models to C for fun | Max Bernstein home blog microblog favorites pl resources bread recipes rss Compiling ML models to C for fun September 19, 2023 NOTE: This post is going to be a compiler post, not a machine learning tutorial, so please treat it as such. Maybe it will still help you understand ML through a compilers lens. I had a nice chat with my friend Chris recently. He walked me through the basics of machine learning while I was looking at Andrej Karpathy ’s micrograd . If you are unfamiliar, micrograd is a very small implementation of a scalar-valued neural network (as opp
Explore this link on the map →saved by
related reading
- A friendly introduction to machine learning compilers and optimizershuyenchip.com
- microgptkarpathy.github.io
- Calculus on Computational Graphs: Backpropagation -- colah's blogcolah.github.io
- Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
- Building a Language and Compiler for Machine Learningjulialang.org
- Composer2.pdfcursor.com
- The Little Book of Deep Learningfleuret.org
- Differentiable Programming from Scratchthenumb.at
- UW PLSE | How does torch.compile work?uwplse.org
- Machine Learning System Resources | std::bodun::blogbodunhu.com
- Tiny TPUtinytpu.com
- Advancements in machine learning for machine learningblog.research.google