tatef4d ago

Hypura – A storage-tier-aware LLM inference scheduler for Apple Silicon

https://github.com/t8/hypura

GitHub - t8/hypura: Run models too big for your Mac's memory

Run models too big for your Mac's memory. Contribute to t8/hypura development by creating an account on GitHub.

GitHub
Show threadbaq4d ago
Intel Optane rolling in its grave.
Show threadspeedgoose
Is it too late for Intel to bring them back to life?
Mar 24 at 5:29pmWeb
Show threadc0balt4d ago
Yes, their NAND division has been sold, it is now mostly under solidigm. Maybe solidigm could bring it back, but it seems unlikely (given the previous commercial failure).