Alternatives
Products that do what Subquadratic LLM Solution does
Subquadratic LLM Solution
- 1
- 2KR
I 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…
2025 · github.com
- 3TV
May 2026 · github.com
- 4IV
The video demo runs a 7b Model on a normal gaming GPU. I think it already works quite well (accounting for the limited hardware power). :)
2024 · github.com
- 51B
Mar 2026 · prismml.com
- 6
Trace LLM requests + costs with OpenTelemetry monitoring
Oct 2025
- 7YA
Built this for my LLM workflows - needed searchable, persistent memory that wouldn't blow up storage costs. I also wanted to use it locally for my research. It's a content-addressed storage system with block-level deduplication (saves 30-40% on typical codebases). I have integrated the CLI tool into most of my workflows in Zed, Claude Code, and Cursor, and I provide the prompt I'm currently using in the repo. The project is in C++ and the build system is rough around the edges but is tested on macOS and Ubuntu 24.04.
2025 · github.com
- 8
- 9TW
Apr 2026 · github.com
- 10WM
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…
2024 · glhf.chat
- 11
- 12
- 13OS
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,…
2024 · getindexify.ai
- 14
- 15LT
Current AI-assisted CLI tools are often part of larger systems and work better on Linux. I built llm-term to address these. It's a Rust-based tool that compiles into a single binary file. You only need to download the binary, add it to your PATH, and configure your OpenAI key to get started. While llm-term offers an option for gpt-4o, it works great with gpt-4o-mini. So it's not costly. I appreciate any feedback or suggestions.
2024 · github.com
- 16IG
2024 · columns.ai
- 17FL
Long-session LLM memory degradation (entropy) is the silent killer of complex coding projects. Models like Gemini, GPT-4, and Claude all suffer from it, leading to hallucinations and lost context. I've developed an open-source protocol that temporarily "fixes" this issue by structuring the dialogue. It's not the final architectural solution, but it’s a proven patch for developers working right now. Looking for feedback from the community on how we can solve this structurally. https://github.com/robertomisuraca-blip/LLM-Entropy-Fix-Prot...
Nov 2025 · github.com
- 18OO
Hey HN, we're super excited to share something we've been working on: OpenLIT. After an engaging preview that some of you might recall, we are now proudly announcing our first stable release! *What's OpenLIT?* Simply put, OpenLIT is an open-source tool designed to make monitoring your Large Language Model (LLM) applications straightforward. It’s built on OpenTelemetry, aiming to reduce the complexities that come with observing the behavior and usage of your LLM stack. *Beyond Basic Text Generation:* OpenLIT isn’t restricted to just text and chatbot outputs. It now includes automatic…
2024 · github.com
- 19LA
G'day, HN! I'm one of the maintainers of `llm`. I've been working alongside a trusty group of contributors to bring this project to life, and we're now at a point where we're ready to share it with the world. Large language models (LLMs) are taking the computing world by storm due to their emergent abilities that allow them to perform a wide variety of tasks, including translation, summarization, code generation, and even some degree of reasoning. However, the ecosystem around LLMs is still in its infancy, and it can be difficult to get started with these models. `llm` is a one-stop shop for…
2023 · github.com
- 20
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)
Jun 2026 · github.com
- 21
I 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.
24d ago · github.com
- 22SE
Good morning HN! For a while now I have been toying with this idea and now finally have a working prototype. This project allows you to encode secret messages into ordinary looking text by using arithmetic coding with a probability model derived from an LLM. By encrypting the message and then decompressing the encrypted message using the arithmetic coder, you get output which looks just like randomly sampled output from the LLM. Except, it actually encodes your secret messages in the specific choices of tokens. By using authenticated encryption, only a user who knows the key can know that a…
2025 · github.com
- 23
Zero-Copy Context Bridging Gateway for Multi-Agent GPU Inference. Bypasses the expensive prefill phase by dynamically stitching KV Caches at the memory level using PagedAttention. Cuts TTFT latency by up to 25x and saves 40%+ VRAM for collaborative LLM workflows. - DaqulaLin/MemStitch
Jul 2026 · github.com
- 245L
We've built InferX, a specialized runtime environment that fundamentally changes how LLMs are served. The core problem we solve is the latency bottleneck in AI inference, especially with large models. Current systems waste resources or suffer from painfully slow cold starts. InferX's AI-native architecture, with its "snapshot" technology, enables: * *Sub-2s cold starts:* Spin up models instantly. * *High density:* Serve more LLMs on the same GPUs. * *Optimal efficiency:* Maximize GPU utilization. This isn't just another API; it's a new execution layer designed from the ground up for the…
2025 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →