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)
KV-psi, using Linux PSI to to trim an LLM KV cache launched on June 27, 2026 with 8 votes, #1,599 of 22,647 launches that month and more than 75% of that year's launches.
What it does
Use Linux Pressure Stall Information to trim an LLM KV cache - infiniteregrets/kv-psi
PSI KV Governor is a small reference implementation for using Linux Pressure Stall Information to trim an LLM KV cache when the system is under memory pressure. cat /proc/pressure/memory PYTHONPATH=src python benchmarks/pressure_bench.py --preflight-only Basic Usage Run the reference simulator: PYTHONPATH=src python -m psi_kv_governor.cli simulate Build the llama.cpp runner: scripts/build_llama_runner.sh Download the small benchmark model if needed: python scripts/download_demo_model.py PSI Benchmark Run both variant orders. This matters because PSI avg10 , cache, and zram/swap state can carry over from the first pressure run into the second. PYTHONPATH=src python…from github.com
Does a similar job
all alternatives →
KVSplit – Run 2-3x longer contexts on Apple Silicon2025 · github.com · ▲272I discovered that in LLM inference, keys and values in the KV cache have very different quantization sensitivities. Keys need higher precision than values to maintain quality. I patched llama.cpp to enable different bit-widths for keys vs. values on Apple Silicon. The results are surprising: - K8V4 (8-bit keys, 4-bit values): 59% memory reduction with only 0.86% perplexity loss - K4V8 (4-bit keys, 8-bit values): 59% memory reduction but 6.06% perplexity loss - The configurations use the same number of bits, but K8V4 is 7× better for quality This means you can run LLMs with 2-3× longer…
Find the best local LLM for your hardware, ranked by benchmarksMay 2026 · github.com · ▲283Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly. - Andyyyy64/whichllm
Shoehorn, a library to quantize an LLM to fit your Mac's VRAMAug 2026 · github.com · ▲6I made this after seeing someone posit the idea online yesterday over lunch then spent some time refining it. So far it's pretty impressive IMO! Right now I am running Qwen3-30B-A3B on my 24gb unified memory m4 MacBook Pro at 50 tok/sec and this should definitely not be working for such a large model on my middling hardware. Things are detailed in the README to get up and running and DESIGN.md has details on all the choices and such made along the way.
Cuts Long Horizon Inference Costs by 50% via external KV Cache OffloadJul 2026 · github.com · ▲22Hey HN, we’re the developers of OpenLake, an open source storage engine for offloading LLM KV caches from GPU memory into a shared tier of RAM and NVMe. We built OpenLake because KV caches are outgrowing GPU memory. A single 256K token conversation on Gemma 4 31B produces approximately 43GB of KV state, more than half the memory of an 80GB H100. The problem becomes even harder across a cluster: a prefix cached on one GPU host is unavailable when the next request lands on a different GPU, forcing the new GPU to repeat work the fleet has already completed. Once the KV cache is offloaded,…
We Beat MLPerf: Modern Storage for KV Offload and LLM TrainingSep 2026 · theopenlake.com · ▲35High performance storage engine for efficient LLM inference and GPU Training.
Plock: Use a local LLM from anywhere in your OS2024 · github.com · ▲6After seeing a cool demo of a hack on Twitter, I built a cross platform version of it that works well and uses streaming. From anywhere on Mac and Linux, trigger Ollama and optionally feed it your clipboard. I built it yesterday and it's already very useful to me. I'm pretty excited about it and wanted to share!
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 22d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 23d ago · fastrouter.ai
Source: Show HN post ↗
Launched alongside, June 2026
the whole month →
Fundraisly▲1,537AI fundraising agent that finds investors and books meetings
AI · Jun 2026 · fundraisly.com
Homebrew 6.0.0▲1,481Today, I’m proud to announce Homebrew 6.0.0. The most significant changes since 5.1.0 are a new tap trust security mechanism, the new faster, smaller, default internal Homebrew JSON API, sandboxing on Linux, better defaults informed by our user survey, many brew bundle improvements, improved performance and initial support for macOS 27 (Golden Gate). Happy to discuss any questions here!
Dev tools · Jun 2026 · brew.sh
Hi HN! I was super frustrated at apps like tiktok and wechat preventing me from saving or downloading the animated gifs, so I made a little tool to turn a screen recording into a slack-sized emoji. Hope you get some value from this!
Life & fun · Jun 2026 · vorpus.github.io
Search 18 years of Hacker News and chart how any topic, tool, or person trended. Overlay terms to compare their rise and fall across 45M posts and comments.
Life & fun · Jun 2026 · hackernewstrends.com