Epoll is a readyness notification API. You tell epoll which fd's you're interested in, then you run a poll operation which blocks until at least one of the fd's you're interested in is ready. Then you separately need to do the actual IO (which is essentially just a memcpy() between kernel and user space).
In contrast io_uring is a completion notification API. You give it a buffer to read or write from/to, and it'll notify you when the IO has been completed.
Io_uring is also more flexible, and can for example be used for disk IO which epoll can't.
Makes sense. Also makes for much more efficient data polling since you get the buffer completed but not a random fd on which to perform yet another syscall.
In contrast io_uring is a completion notification API. You give it a buffer to read or write from/to, and it'll notify you when the IO has been completed.
Io_uring is also more flexible, and can for example be used for disk IO which epoll can't.