From another thread:
Bitcoin is mostly hashing, so most of an ASIC would be SHA256 cores stamped out side by side on the chip. Such cores are fairly compact.
I'm not a Litecoiner, but I believe they have it set to require 128KiB of memory per core. That means you have to stamp out (core) (128KiB) (core) (128KiB) across the chip; therefore you get far fewer cores per chip.
The alternative is to have an ASIC with a memory bus to some external DRAM chips. That makes the RAM cheap but you now have to get a much bigger ASIC for all the bus lines, and you still won't get very many cores on a chip before the RAM speed becomes a bottleneck.
Originally people thought the RAM requirement would prevent GPUs from being useful at all. That was wrong, but I don't think they can escape the RAM bottleneck generally, so ASICs, like GPUs, will be limited mostly by the RAM you can attach. That might change if someone can put together an inexpensive ASIC with RAM on die. I don't expect that to happen faster than the rate GPU-mem-bandwidth-per-dollar increases, but you never know.
I do think LTC was too conservative with their memory size. They were trying to keep it in L2 cache to keep it targeted at general purpose processors, but I think they would have done better requiring a few hundred megs per core.
tldr: If there ever is an ASIC for scrypt, it won't be one that gives a improvement two orders of magnitude over GPUs like SHA256 ASICs gave.
