Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

MinIO is a high-performance, S3 compatible object store, open sourced under GNU AGPLv3 license.

MinIO Object Storage Documentation

Stress Testing Embedding Models

LLM inference in C/C++

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus Agent Tools, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae…

A daemon that automatically manages the performance states of NVIDIA GPUs.

The main repository for building Pascal-compatible versions of ML applications and libraries.

Module, Model, and Tensor Serialization/Deserialization

Simple high-throughput inference library

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

The Sesame AI Labs CS Generation Model

A fork of vLLM enabling Pascal architecture GPUs

DeepSeek-VL: Towards Real-World Vision-Language Understanding

CI scripts designed to build a Pascal-compatible version of Triton.

Custom Component for ESPHome enabling Serial over TCP

Colbert and DPR search on wikipedia datasets

Write a simple interpreter of C. Inspired by c4 and largely based on it.