Matt Rutkowski

LLM inference in C/C++

No description provided.

A taxonomy of all official CycloneDX property namespaces and names

A library to identify and format deltas between JSON data sets

No description provided.

Tools to help debugging models within the HF Transformer framework

Creates CycloneDX Software Bill-of-Materials (SBOM) for Node.js, Java, Python and golang projects from source and container images

A framework for few-shot evaluation of language models.

NVIDIA’s repository for enabling trustworthy AI.

No description provided.

IBM GGUF-encoded AI models and conversion scripts

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, and other large language models.

Utility that provides an API and CLI to identify licenses and legal terms

Utility that provides an API platform for validating, querying and managing BOM data

Notes from the DeepLearning.AI courses

A minimalistic C++ Jinja templating engine for LLM chat templates

OASIS Open Repository: Manages TOSCA Simple Profile in YAML templates and definitions that can be used to test TOSCA compliance using metadata (primarily the OASIS Test Assertion Markup Language) that describes the test and the expected behavior of the TOSCA tool or orchestrator

No description provided.

Granite Snack Cookbook -- easily consumable recipes (python notebooks) that showcase the capabilities of the Granite models

Perplexica is an AI-powered search engine. It is an Open source alternative to Perplexity AI

CycloneDX is a full-stack Bill of Materials (BOM) standard that provides advanced supply chain capabilities for cyber risk reduction. SBOM, SaaSBOM, HBOM, ML-BOM, OBOM, MBOM, VDR, and VEX

:robot: The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. Features: Generate Text, Audio, Video, Images, Voice Cloning, Distributed, P2P inference

The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, and more.

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

All about mrutkows

:mag_right: ScanCode detects licenses, copyrights, package manifests & dependencies and more by scanning code ... to discover and inventory open source and third-party packages used in your code.

🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools

Easy, fast and very cheap training and inference on AWS Trainium and Inferentia chips.

Taxonomy tree that will allow you to create models tuned with your data