Stars
Media decoding and encoding for PyTorch: videos, images, and audio, on CPU and GPU.
Fast Open-Source Search & Clustering engine × for Vectors & Arbitrary Objects × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍
🍡 30x faster tokenization for every HuggingFace model
Mount Hugging Face Buckets and repos as local filesystems. No download, no copy, no waiting.
A fast, streaming-friendly BM25 search engine in Rust with mmap support
A lightweight, open-source, fully local alternative to Logitech Options+ for remapping Logitech HID++ mice.
Zotero is a free, easy-to-use tool to help you collect, organize, annotate, cite, and share your research sources.
A CLI to estimate inference memory requirements for Hugging Face models, written in Python.
Peek inside Parquet files right from your terminal
Warcraft III Peon voice notifications (+ more!) for Claude Code, Codex, IDEs, and any AI agent. Stop babysitting your terminal. Employ a Peon today.
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
NextPlaid, ColGREP: Multi-vector search, from database to coding agents.
Nearly Inference Free Embeddings: make your RAG queries 500x faster
Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀
TF-ID: Table/Figure IDentifier for academic papers
Move and resize windows on macOS with keyboard shortcuts and snap areas
Github homepage releases feed is always broken - so I created my own
Provide with pre-build flash-attention 2 and 3 package wheels on Linux and Windows using GitHub Actions
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
The training codes of Jasper-Token-Compression-600M
A modern static site generator by the Material for MkDocs team
Automating Releases via SemVer and Commit Message Conventions