dipampaul17 / KVSplitLinks
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.
☆362Updated 7 months ago
Alternatives and similar repositories for KVSplit
Users that are interested in KVSplit are comparing it to the libraries listed below
Sorting:
- High-Performance Implementation of OpenAI's TikToken.☆467Updated 6 months ago
- Add object detection, tracking, mobile notifications, and search to any security camera.☆513Updated this week
- Browser-LLM Auto-Scaling Technology☆768Updated last week
- Attempt to create an Open Source Privacy Focused Rewind.ai Alternative that is a POD (Personal Online Datastore)☆227Updated 3 months ago
- ☆280Updated 7 months ago
- ☆200Updated 8 months ago
- Persistent memory for LLMs and apps. Content-addressed storage with dedupe, compression, full-text and vector search.☆362Updated this week
- CLI app- Give it a YouTube URL and you get a transcription with possible speaker identification and optional summary or translation, all …☆329Updated last month
- state of the art browsing agent (WebArena 72.7%)☆363Updated 3 months ago
- Docker-based inference engine for AMD GPUs☆231Updated last year
- An open-source framework for verifiably private AI inference☆905Updated last week
- This project collects GPU benchmarks from various cloud providers and compares them to fixed per token costs. Use our tool for efficient …☆222Updated last year
- Physical AI Assistant that illuminates your life☆191Updated 3 months ago
- ☆164Updated 9 months ago
- CleverBee - The Open Source Deep Researcher Tool☆310Updated 7 months ago
- Git Based Memory Storage for Conversational AI Agent☆768Updated last month
- Fully neural approach for text chunking☆406Updated 2 months ago
- Applying the ideas of Deepseek R1 to computer use☆221Updated 11 months ago
- A secure local sandbox to run LLM-generated code using Apple containers☆711Updated last month
- Examples and guides for using the VLM Run API☆305Updated 2 weeks ago
- https://ensue.dev☆381Updated this week
- A lightweight text-to-speech model with zero-shot voice cloning☆736Updated last week
- Spegel - Reflect the web through AI☆332Updated 6 months ago
- A hub for various industry-specific schemas to be used with VLMs.☆539Updated last month
- Multimodal RAG to search and interact locally with technical documents of any kind☆284Updated 2 months ago
- Run and explore Llama models locally with minimal dependencies on CPU☆190Updated last year
- Decrypted Generative Model safety files for Apple Intelligence containing filters☆310Updated 2 months ago
- Fact Graph☆377Updated 2 months ago
- ai for jq☆249Updated last year
- A comprehensive suite of tools, built to liberate science by making the creation, evaluation, and dissemination of research more transpar…☆230Updated 5 months ago