🤗 Optimum ONNX: Export your model to ONNX and run inference with ONNX Runtime

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

GPU-accelerated Llama3.java inference in pure Java using TornadoVM.

PyTorch media decoding and encoding

PyTorch native quantization and sparsity for training and inference

A low-dependency Scala library providing a cached variable that self-updates periodically, and a periodic function runner

Adding guardrails to large language models.

Open-source search and retrieval database for AI applications.

DSPy: The framework for programming—not prompting—language models

Everything about the SmolLM and SmolVLM family of models

Friendly fork of Scala.js, target stand-alone Wasm leveraging WASI and Component Model

A cross compiled Scala 3 library that provides accessible functionality to generate, manipulate, and export 3D mesh objects. Currently supports .PLY, and .OBJ/.MTL file formats.

Drivers and libraries for the Xbox Kinect device on Windows, Linux, and OS X

Examples of using Scala 3 Native to interop with various C libraries using sn-bindgen

Toolkit for Scala Development

A bleeping fast scala build tool!

Scala 3 Open Community Build - detects regressions in the Scala 3 compiler based on the Open Source Scala 3 ecosystem

Exports OpenAI Whisper speech recognition models to ONNX. Mainly intended for use with Echogarden.

dhtcrawler is a DHT crawler written in erlang. It can join a DHT network and crawl many P2P torrents. The program save all torrent info into database and provide an http interface to search a torre…

ONNX-backed array library that is compliant with the Array API standard.

A blazingly fast multi-language serialization framework powered by JIT and zero-copy.

Generative AI extensions for onnxruntime

A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences

A user-friendly tool chain that enables the seamless execution of ONNX models using JAX as the backend.