Show HN: High speed graphics rendering research with tinygrad/tinyJIT (github.com)
I saw a tweet that tinygrad is so good that you could make a graphics library that wraps tg. So I’ve been hacking on a gtinygrad, and honestly it convinced me it could be used for legit research.
The JIT + tensor model ends up being a really nice way to express light transport all in simple python, so I reimplemented some new research papers from SIGGRAPH like REstir PG and SZ and it just works. instead of complicated cpp its just a 200 LOC of python.
4 comments
[ 2.6 ms ] story [ 19.3 ms ] threadhttps://blog.evjang.com/2019/11/jaxpt.html is a better demo of how to render the Cornell Box on a TPU using differentiable path tracing.