New CRAM method offers giant boost to compressed memory reads

https://downloadmoreram.com/

Whoa, new options! I'm downloading the Quantum RAM with Haptic Feedback.

probably not to your current computer. this works on supporting memory types that do compression in hardware.

You wouldn't download a car

Unfortunately the recording is missing audio for half the talk. A frequent issue for the plumbers livestreams this year.

https://www.youtube.com/live/OPRciCSsdS4?t=2031

Added above. Thanks!

Thank you <3

It's not really about hardware offload, the biggest problem with zswap is that it's swap. The rest of the kernel treats it like a fast SSD (which is still incredibly slow compared to RAM) instead of slower memory that needs a bit of special handling on writes.

NUMA maps a lot closer to what compressed RAM actually is. The subsystem is more aware of CRAMs specifics so it can make better decisions about where to put allocations and everything gets faster. And it's less overhead because swap is not really optimized for frequent direct access but for NUMA it's the most basic function.

We brute force AI models right now because a) we don’t know better, and b) it’s premature optimization.

I beg to differ on point b, but no one is delaying their next model just so they can concentrate on optimization.

It’s coming though.

One example: https://siliconangle.com/2026/07/28/ai-model-compression-sta...

Another is separating the the intelligence part of the model from the known facts part of the model (which can be better compressed)

Compression doesn't really work for model weights.

Model quantization and model distillation are two techniques to reduce model size.

one would hope model weights are already high entropy enough and would not be improved by a general-purpose memory compression algo?