KV-psi
using Linux PSI to to trim an LLM KV cache. Use Linux Pressure Stall Information 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.
Open source
Reactions (1)
Similar products
by description similarity
KVSplit
github.comRun 2-3x longer contexts on Apple Silicon
Lowfat
github.compluggable CLI filter that saved 91.8% of my LLM tokens
OpenLake is a high performance storage engine for efficient LLM inference and GPU Training
Cachet
github.comA drop-in semantic cache for LLM APIs, 100% local, in Rust
Llmbuffer
github.comPython library for cache-optimized LLM conversation history