Run larger LLMs with longer contexts on Apple Silicon by using differentiated precision for KV cache quantization. KVSplit enables 8-bit keys & 4-bit values, reducing memory by 59% with <1% quality loss. Includes benchmarking, visualization, and one-command setup. Optimized for M1/M2/M3 Macs with Metal support.
☆361May 21, 2025Updated 11 months ago
Alternatives and similar repositories for KVSplit
Users that are interested in KVSplit are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Merliot Device Hub☆166Jun 11, 2025Updated 10 months ago
- Fully neural approach for text chunking☆407Oct 23, 2025Updated 6 months ago
- Artificial Neural Engine Machine Learning Library☆1,592Mar 10, 2026Updated last month
- Docker-based inference engine for AMD GPUs☆233Oct 7, 2024Updated last year
- A simple alternative to homebrew for installing binary packages on MacOS & Linux written in Go.☆219Apr 29, 2026Updated last week
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆10Feb 14, 2025Updated last year
- A browser-based, WebGL2 implementation of GPT-2 with transform block and attention matrix visualization☆342Oct 24, 2025Updated 6 months ago
- Erlang interpreter for Node-RED (visual flow based programming) with Elixir support☆333Apr 3, 2026Updated last month
- ☆198May 5, 2025Updated last year
- A powerful document AI question-answering tool that connects to your local Ollama models. Create, manage, and interact with RAG systems f…☆1,096Aug 9, 2025Updated 8 months ago
- World's first Nintendo 3DS emulator for Apple devices based on Citra.☆18Apr 7, 2023Updated 3 years ago
- High-Performance Implementation of OpenAI's TikToken.☆475Jul 3, 2025Updated 10 months ago
- https://ollama.com/search?o=newest☆34Updated this week
- Min.js Style Compression of Tech Docs for LLM Context☆678Oct 5, 2025Updated 7 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Official Rust Implementation of Model2Vec☆179Apr 10, 2026Updated 3 weeks ago
- Multi-modal OCR pipeline optimized for ML training (text, figure, math, tables, diagrams)☆682May 20, 2025Updated 11 months ago
- Rewriting Principia Mathematica in Lean☆137Feb 5, 2026Updated 3 months ago
- Browser-LLM Auto-Scaling Technology☆777Jan 29, 2026Updated 3 months ago
- Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.☆630Feb 24, 2025Updated last year
- Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full…☆15,318Apr 27, 2026Updated last week
- High performance Rust stream processing engine seamlessly integrates AI capabilities, providing powerful real-time data processing and in…☆1,272Apr 27, 2026Updated last week
- Pytorch script hot swap: Change code without unloading your LLM from VRAM☆125Apr 21, 2025Updated last year
- LLM plugin for pulling content from Hacker News☆128May 5, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Resource (icon) extraction tools☆13Apr 22, 2024Updated 2 years ago
- Transductive regular expressions☆257Sep 25, 2025Updated 7 months ago
- VPN over UDP☆114Feb 3, 2026Updated 3 months ago
- Server for Matching Long/Lat to Timezone