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

Community maintained hardware plugin for vLLM on Spyre

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Build Research and Rag agents with Granite on your laptop

Cloud Native Benchmarking of Foundation Models

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

Large Language Model Text Generation Inference

A fork of github.com/vllm-project/vllm

Simple, safe way to store and distribute tensors

Geospatial Data Science with Julia

Apache Iceberg (Incubating)

A Dockerised django CMS project, ready to deploy on Divio or another Docker-based cloud platform, and run locally in Docker on your own machine. A Divio account is not required.

Stocator is high performing connector to object storage for Apache Spark, achieving performance by leveraging object storage semantics.

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads.

Enables Ray to use IBM Gen2 backend

Module to provision rosa on aws

Community driven, reusable components for distributed apps

Machine Learning Toolkit for Kubernetes

Kubeflow Pipelines on Tekton

A parser for the SPARQL query language in JavaScript

Allow the helm commands to take folders as value-specifications

JSON Web Tokens for Lua

Kubernetes Mutating Admission Webhook for dnsconfig pod injection

Distributed Task Queue (development branch)

Unofficial maintenance repository of Torch7. It supports CUDA10.1, Volta, Docker https://hub.docker.com/r/nagadomi/torch7