GPU-accelerated Llama3.java inference in pure Java using TornadoVM.
-
Updated
Sep 13, 2026 - Java
GPU-accelerated Llama3.java inference in pure Java using TornadoVM.
A self-hosted, privacy-focused RAG (Retrieval-Augmented Generation) interface for intelligent document interaction. Turn any document into a knowledge base you can chat with.
An intelligent, low-latency local LLM router that reduces AI costs by 30-70%. Uses a self-hosted classifier to automatically route prompts to the most cost-effective model without external API overhead.
A minecraft 26.1.2 spigot plugin allows to easily break language barriers by using ollama on the server to translate all messages into a specfic target language.
CodeNova is an AI-powered coding assistant that enhances software development by automating code generation, debugging, documentation, and explanations. Built for the Generative AI Hackathon with IBM GRANITE, it integrates advanced AI models to streamline development workflows and provide business-valued solutions.
Real-time AI-powered racing safety platform that predicts circuit risk using weather data, historical incidents, and IBM Granite AI.
Local OBD-II anomaly-risk analysis and owner-facing reporting with IBM Granite TTM, RAG and validated LLM outputs.
Voronoi spatial analytics and an explainable-AI tactical analyst for soccer tracking data, powered by the IBM Granite LLM ? Streamlit app over StatsBomb freeze-frames
Python sustainability climate-change biodiversity restoration multi-agent-system generative-ai agentic-ai ibm-granite ibm-adk groq-api.
SGLang fork for IBM POWER9 (ppc64le): Tesla V100 sm70, CUDA 12.4, Granite LLM inference. Triton attention, float16, OpenAI-compatible API.
A list of Edge optimized Ollama models
Agentic AI Interview Trainer powered by IBM watsonx Orchestrate, IBM Granite and RAG
AI-powered monitoring, forecasting, simulation and decision support for hybrid solar and wind energy systems.
Schaapje - A Dutch Small Language Model
DecisionLens: A Corrective RAG Engine for IFAB/FIFA Rule Compliance and VAR Transparency
Real-time, screen-reader-native, IFAB-grounded AI explainer of VAR and offside decisions for blind fans. IBM SkillsBuild June 2026.
Sovereign Pit-Wall: A zero-latency edge architecture pairing a custom VFS with IBM Granite. It syncs F1 mechanical telemetry with driver biometrics to predict catastrophic failures in real-time.
A collection of powerful aviation utility endpoints: great-circle distance between airports, navigation aid search (VOR/NDB/ILS/DME), FAA NAS delay status, AI-powered flight briefings, and ML-predicted gate-to-gate flight times.
AI Legal Contract Advisor - Multi-agent AI system for legal contract analysis powered by IBM watsonx Orchestrate. Fuses regulatory signals from 10+ sources to deliver transparent legal reasoning with full traceability. Built for IBM Dev Day AI Demystified Hackathon 2026.
Coordinate agent brainstorming to generate research proposals and manage future experiment and review workflows
To associate your repository with the ibm-granite topic, visit your repo's landing page and select "manage topics."