Viewing profile — zander_jiang

The book is really well written.

I wonder what happens to fireworks ai, who provided the infra to train and serve composer 2, cursor was their largest customer, and they're probably loosing it.

tilert is a highly optimized megakernel, its a single kernel that does the entire decode pass, this enables overlapping weight loading with computation, eliminates cuda launch over…

tilert is closed source, the repo is just a python wrapper that invokes the binary.