KV-psi, using Linux PSI to to trim an LLM KV cache
KV-psi, using Linux PSI to to trim an LLM KV cache
I thought it'd be interesting to use Linux PSI (Pressure Stall Information) for an LLM runtime to trim the KV cache. This is mainly useful imo for edge devices like the Jetson Orin super nano kit which have unified memory. I haven't benched much, but plan to do so more over time and see if I can make a real use of it as I run local LLMs. Let me know if it makes sense :P (I of course vibed this idea)
Share cardActual performance
Launch Intel predictions
Analyze your own launch →Correct prediction on native model
Similar products
Credentials dumper for Linux using eBPF
Guiding LLM outputs using Zod
Variant Symlink Filesystem for Linux
Distributed memcached in Linux kernel
Compressed directories on Linux
Sqlite3-X64 – SQLite Precompiled Binaries for Linux X64
ExpanDrive for Linux
An Aesthetically Pleasing Arch Linux Distro
CoreOS, a Linux distro for containers
2048.ko: 2048 as a linux kernel module