Glommio is a thread-per-core crate that makes writing highly parallel asynchronous applications in a thread-per-core architecture easier for rustaceans.

The Cloud Native Application Proxy

Contexts Optical Compression

StreamingVLM: Real-Time Understanding for Infinite Video Streams

Process execution for humans

Universal markup converter

Fully open reproduction of DeepSeek-R1

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

FastAPI framework, high performance, easy to learn, fast to code, ready for production

Fastest kernels written from scratch

The Inter font family

Fast CUDA matrix multiplication from scratch

Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.

An idiomatic, lean, fast & safe pure Rust implementation of Git

Learn how to design systems at scale and prepare for system design interviews

Like NumPy, in JavaScript

transparently encrypt files within a git repository

HarfBuzz text shaping engine

Amiri (أميري) is a body text Naskh typeface

A unified library of state-of-the-art model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment…

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

Efficient Triton Kernels for LLM Training

Optimized primitives for collective multi-GPU communication

The LLM Evaluation Framework

Universal memory layer for AI Agents