Cuts Long Horizon Inference Costs by 50% via external KV Cache Offload
Hey 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,…
In plain words
OpenLake is an open source storage engine that offloads large language model KV caches from GPU memory to shared RAM and NVMe storage. It addresses the problem of KV caches exceeding GPU capacity during long conversations and across distributed clusters. The tool includes a custom CUDA kernel for lossless compression to reduce network overhead when retrieving cached data. It is designed for developers and organizations running LLM inference at scale who need to reduce memory constraints and improve efficiency.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey 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, network bandwidth becomes a major constraint on read latency. To move less data across the wire, we built deferred materialization: a custom CUDA kernel that losslessly compresses KV blocks before they leave GPU memory and decompresses them on the GPU after retrieval. In our tests, this achieved: - 1.72× lossless KV compression. - Approximately 600GB/s decompression throughput on an H100 - 80GB/s of effective KV throughput over a physical 50GB/s link At 128K context, retrieving cached KV reduces TTFT from 44 seconds to 0.6 seconds, a 66× improvement. Across the complete workload, GPU time reduces from 1,169 seconds to 606 seconds, saving 48.2% of GPU cost. OpenLake is written in Rust and uses io_uring with one pinned runtime per physical core. We provide connectors for vLLM and SGLang so the cache can be enabled without modifying the inference engine itself. I would love to hear how others are handling KV reuse across GPU hosts, especially for long contexts, and get to know your thoughts. Thanks! GitHub: https://github.com/openlake-project/openlake Here is our blog: https://cloud.theopenlake.com/blog/taming-the-beast-managing...
Does the same job
all alternatives →
We Beat MLPerf: Modern Storage for KV Offload and LLM Training22h ago · theopenlake.com · ▲35High performance storage engine for efficient LLM inference and GPU Training.
- OSOpen-source engine running Gemma 4 26B in 2 GB RAM on any M-series MacJul 2026 · github.com · ▲919
Hi HN, I built a specialized inference engine for running 4-bit Gemma 4 26B-A4B-IT on any M-series Mac using about 2 GB of RAM. It is called TurboFieldfare and is written in Swift and Metal. I have always adored on-device AI. It feels like magic that you can run a powerful NN on your Mac or iPhone. So I wanted to push the limits a bit and run a model whose weights don’t fit in memory. The model’s 4-bit quantized weights occupy roughly 14 GB, which makes running it with conventional inference tools almost impossible on an 8 GB or even 16 GB Mac once the OS, applications, and KV cache are…
- WMWe made glhf.chat – run almost any open-source LLM, including 405B2024 · glhf.chat · ▲161
Try it out! https://glhf.chat/ Hey HN! We’ve been working for the past few months on a website to let you easily run (almost) any open-source LLM on autoscaling GPU clusters. It’s free for now while we figure out how to price it, but we expect to be cheaper than most GPU offerings since we can run the models multi-tenant. Unlike Together AI, Fireworks, etc, we’ll run any model that the open-source vLLM project supports: we don’t have a hardcoded list. If you want a specific model or finetune, you don’t have to ask us for it: you can just paste the Hugging Face link in and…
- OSOpen-source real time data framework for LLM applications2024 · getindexify.ai · ▲92
Hey HN, I am the founder of Tensorlake. Prototyping LLM applications have become a lot easier, building decision making LLM applications that work on constantly updating data is still very challenging in production settings. The systems engineering problems that we have seen people face are - 1. Reliably process ingested content in real time if the application is sensitive to freshness of information. 2. Being able to bring in any kind of model, and run different parts of the pipeline on GPUs and CPUs. 3. Fault Tolerance to ingestion spike, compute infrastructure failure. 4. Scaling compute,…
- TVTiny-vLLM – high performance LLM inference engine in C++ and CUDAMay 2026 · github.com · ▲205
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, July 2026
the whole month →- IR
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…
Life & fun · Jul 2026
- EElevators▲1,680
Life & fun · Jul 2026 · john.fun
- 1W18 Words▲1,160
Life & fun · Jul 2026 · 18words.com
- BA
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…
Dev tools · Jul 2026 · bento.page
- GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI · Jul 2026 · github.com
