Visualize streams of multimodal data. Free, fast, easy to use, and simple to integrate. Built in Rust.

Faster Whisper transcription with CTranslate2

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

Github action to retrieve all (added, copied, modified, deleted, renamed, type changed, unmerged, unknown) files and directories.

Prefect is a workflow orchestration framework for building resilient data pipelines in Python.

Open source API development ecosystem - https://hoppscotch.io (open-source alternative to Postman, Insomnia)

A hyperparameter optimization framework

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Cython wrapper for the C++ translation of the Angus Johnson's Clipper library (ver. 6.4.2)

Manipulation and analysis of geometric objects

Fast Automatic License Plate Recognition (ALPR) framework.

Database diagrams editor that allows you to visualize and design your DB with a single query.

A GitHub Action to generate semantic version from a git repository's commit history.

Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.

Trax — Deep Learning with Clear Code and Speed

DiceDB is a redis-compliant, reactive, scalable, highly-available, unified cache optimized for modern hardware.

Tensor library for machine learning

Minimalist ML framework for Rust

A general fine-tuning kit geared toward diffusion models.

Erasing Concepts from Diffusion Models

Unsupervised text tokenizer for Neural Network-based text generation.

Fixes mojibake and other glitches in Unicode text, after the fact.

Hackable and optimized Transformers building blocks, supporting a composable construction.

This is the repo for our new project Highly Accurate Dichotomous Image Segmentation

⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit for ☁️Cloud 📱Mobile and 📹Edge. Including Image, Video, Text and Audio 20+ main stream scenarios and 150+ SOTA models with end-to-end…

OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference

Fast and memory-efficient exact attention

Monitor Memory usage of Python code

Various AI scripts. Mostly Stable Diffusion stuff.

Accessible large language models via k-bit quantization for PyTorch.