hey,
how does someone get started with doing things like these (writing inference code/ cuda etc..). any guidance is appreciated. i understand one doesn't just directly write these things and this would require some kind of reading. would be great to receive some pointers.
Same! Would love any resources. I'm interested more in making models run vs making the models themselves :)
These are good lectures and there is also a discord. https://github.com/gpu-mode/lectures