A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

Customized ollama models

Agentic Deep Research using open ai agents framework

PostgreSQL extension for BM25 relevance-ranked full-text search. Postgres OSS licensed.

Sharp Monocular View Synthesis in Less Than a Second

Nuitka is a Python compiler written in Python. It's fully compatible with Python 2.6, 2.7, 3.4-3.13. You feed it your Python app, it does a lot of clever things, and spits out an executable or exte…

A DSL for data-driven computational pipelines

Latent Collaboration in Multi-Agent Systems

Git hooks for interacting with LLMs

SwarmUI (formerly StableSwarmUI), A Modular Stable Diffusion Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, and extensibility.

Wan: Open and Advanced Large-Scale Video Generative Models

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…

Send push notifications to your phone or desktop using PUT/POST

Kimi K2 is the large language model series developed by Moonshot AI team

🦉 Data Versioning and ML Experiments

Terraform module which provisions addons on Amazon EKS clusters

CDK construct for installing and configuring Karpenter on EKS clusters

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

KubeFlow on AWS

Contexts Optical Compression

Optimized primitives for collective multi-GPU communication

Microsoft Collective Communication Library

Large Language Model Text Generation Inference

MSCCL++: A GPU-driven communication stack for scalable AI applications

Making dwm as beautiful as possible!

This repository contains the simulation assets for the Mk1 humanoid robot featured in my YouTube video.

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.