Redis for LLMs

A high-throughput and memory-efficient inference and serving engine for LLMs

External logging backend implementation for LMCache

Python framework which enables you to transform how a user calls or infers an IBM Granite model and how the output from the model is returned to the user.

FMS Model Optimizer is a framework for developing reduced precision neural network models.

Open source project for data preparation of LLM application builders

Source code for the IBM Granite Foundational Model Workshop

Granite Time Series Cookbook

Composable building blocks to build Llama Apps

Command-line interface. Use this to chat with the model or train the model (training consumes the taxonomy data)

A repository of utililties that make notebooks look cleaner

Granite Code Cookbook

Python library for Synthetic Data Generation

The Kubernetes Package Manager

This is a Helm plugin which map deprecated or removed Kubernetes APIs in a release to supported APIs

Helm: Kubernetes Package Manager static www

This is a Helm v3 plugin which migrates and cleans up Helm v2 configuration and releases in-place to Helm v3

Design documents that span multiple InstructLab components

Synthetic Data Generation for Foundation Models

InstructLab GitHub organization community files.

Tuning scripts using Hugging Face `SFTTrainer`

Train transformer language models with reinforcement learning.

⚡ Building applications with LLMs through composability ⚡

this is for fun, ain't it grand!

Tensors and Dynamic neural networks in Python with strong GPU acceleration