Educational content, tutorials and insights on the future of AI infrastructure.

Product updates

Introducing Ori Inference Endpoints

Say hello to Ori Inference Endpoints, an easy and scalable way to deploy state-of-the-art machine learning models as API endpoints.

Company News

Ori Welcomes Jacob Smith to Its Board of Directors

Meet Ori's new board member Jacob Smith.

Tutorial

How to run Llama 3.3 70B on a cloud GPU

Learn how to deploy Meta’s new text-generation model Llama 3.3 70B with Ollama and Open WebUI on an Ori cloud GPU.

GPU

An overview of the NVIDIA H200 GPU

Inside the NVIDIA H200: Specifications, use cases, performance benchmarks, and a comparison of H200 vs H100 GPUs.

Tutorial

How to run Genmo Mochi 1 video generation on a cloud GPU

Discover how to deploy Genmo Mochi 1 with ComfyUI on an Ori GPU instance, and read our analysis of this new open source video generation model.

GPU

Everything you need to know about the NVIDIA L40S GPU

Learn more about the NVIDIA L40S, a versatile GPU that is designed to power a wide variety of applications, and check out NVIDIA L40S vs NVIDIA H100...

Company News

Ori Global Cloud deploys a new Private Cloud cluster with 1024 NVIDIA H100 GPUs

Meet Ori Global Cloud's new Private Cloud cluster with 1024 NVIDIA H100 GPUs, designed for massive scale AI with limitless customization.

Case study

nCompass (YC W24) leverages Ori Serverless Kubernetes to make AI inference 2x cost-effective

Find out how Ori Serverless Kubernetes is helping nCompass run cost-effective LLM inference at scale.

AI

Benchmarking Llama 3.1 8B Instruct on Nvidia H100 and A100 chips with the vLLM Inferencing Engine

Benchmarking llama 3.1 8B Instruct with vLLM using BeFOri to benchmark time to first token (TTFT), inter-token latency, end to end latency, and...

Company News

Welcome to the new Ori Global Cloud

Say hello to the new Ori Global Cloud! Our reimagined brand reflects Ori's commitment to driving the future of AI and cloud innovation, enabling...

Tutorial

How to run Llama 3.2 11B Vision with Hugging Face Transformers on a cloud GPU

Learn how to deploy Meta’s multimodal Lllama 3.2 11B Vision model with Hugging Face Transformers on an Ori cloud GPU and see how it compares with...

Tutorial

How to run Pixtral 12B on a cloud GPU with vLLM

Discover how to get Mistral’s new multimodal LLM, Pixtral 12B up and running on an Ori cloud GPU.

Product updates

Ori Global Cloud REST API now generally available

Learn more about Ori Global Cloud REST API which helps you create, access and manage Ori cloud resources programmatically.

Tutorial

How to run Flux.1 image generation on Ori cloud GPUs

Learn how to deploy Flux.1 image generation on the Ori GPU cloud. This tutorial will demonstrate how to create images with Flux's open source...

Company News

Ori Industries and Stelia join forces to build data mobility for the AI era

Ori has partnered with Stelia to enhance AI-driven data processing by integrating Stelia's advanced data mobility platform into Ori's GPU cloud...

Case study

AI Meets Rugby: Framesports automates match analysis on Ori Serverless Kubernetes

Learn how Ori Serverless Kubernetes is helping Framesports analyze Rugby matches with AI.

LLM

Deploy and scale LLMs on Ori Serverless Kubernetes with Ollama and Open WebUI

Learn how to deploy LLMs and scale inference on Ori Serverless Kubernetes, via Ollama and Open WebUI.

Company News

Ori founder and CEO, Mahdi Yahya participates in the AI Action Plan roundtable at 10 Downing Street

Our CEO Mahdi Yahya joined the AI action plan round table at 10 Downing Street to share his insights on supercharging the UK's AI ecosystem

AI

An introduction to AI agents

Agentic AI is the next frontier in AI adoption. Discover more about AI agents in this blog post: what are they, types of agents, benefits, AI agents...

Analysis

A deep dive into NVIDIA’s Blackwell platform: B100 vs B200 vs GB200 GPUs

Explore the NVIDIA Blackwell GPU platform, featuring powerful superchips like B100, B200, and GB200. Discover how these GPUs are about to unleash a...

Product updates

Introducing Ori Serverless Kubernetes

Meet Ori Serverless Kubernetes, an AI infrastructure service that brings you the best of Serverless and Kubernetes by blending powerful scalability,...

AI

How to Perform a Cost-per-Token Analysis of Self-Hosted LLMs Using BeFOri: DBRX from Databricks

Discover how to use BeFOri to calculate a cost per input and output token for self hosted models and apply this methodology to the DBRX Base model...

Case study

Empowering SMBs with AI: How Emediately is building powerful LLM solutions on Ori’s AI Native GPU cloud

Discover how Ori is helping Emediately bring powerful AI solutions to small and medium businesses.

Company News

Ori Welcomes Richard Tame as Chief Financial Officer

Ori hires Richard Tame as Chief Financial Officer announcement

AI

How to run Snowflake Arctic Model Inference on NVIDIA H100s

Ready to experience the Snowflake-Arctic-instruct model with Hugging Face? In this blog we are going to walk you through environment setup, model...

Case study

Basecamp Research uses AI to deliver process-ready proteins faster

Basecamp Research leverages Ori's GPU Cloud to help them deliver more accurate structure predictions, more protein annotations and controllable...

AI

Unveiling a New Benchmarking Framework from Ori

Access BeFOri for LLama2 and LLama3 Benchmarks on Nvidia V100s and H100 Chips

Blog Post

How to Merge Models for Code-Generating LLMs

Generative AI coding is a powerful assistant for software developers. Mergekit offers an easy way to blend pre-trained code LLMs and create your own...

AI

Choosing between NVIDIA H100 vs A100 - Performance and Costs Considerations

When should you opt for H100 GPUs over A100s for ML training and inference? Here's a top down view when considering cost, performance and use case.

General availability of Virtual Machines with NVIDIA GPUs

General availability of Virtual Machines with NVIDIA GPUs (H100, A100, V100) in Ori Global Cloud.

Blog Post

How to Navigate a Global GPU Shortage & Scale AI Workloads

A global GPU shortage and rogue compute costs can threaten to sink even the best AI project’s go-to-market plans. How can AI teams navigate around...

DevOps

The Ori Magic: Orchestrating Inter-cluster Networking in K8s

This deployment walkthrough demonstrates how Ori simplifies and automates complex orchestration tasks, ensuring seamless communication between...

Guide: Integrating Ori with your existing CI/CD pipeline

Explore how to integrate Ori with your existing CI/CD pipelines.

Blog Post

AI at Scale: Deploy LLMs like Code Llama on Any Cloud

Follow this step-by-step guide to quickly deploy Meta’s Code Llama and other open-source Large Language Models (LLMs), using Python and Hugging Face...

Blog Post

Stop Automating, Start Orchestrating!

Successful organisations already operate in terms of objectives and outcomes, and to control the cost of complexity, DevOps automation processes must...

Hands-on Change Data Capture in Go with Postgres and Debezium

Explore a hands-on guide to Change Data Capture in Go with Postgres, Apache Pulsar, and Debezium. Learn to create applications that become reactive...

Migrating a CRA project to Vite.js

Ori's journey from CRA to Vite.js: The challenges we faced, the benefits we reaped, and why we felt the need to make the shift.

Tutorial: Deploying GPU Workloads With Ori and Google Cloud

Learn how to leverage Ori to deploy GPU workloads on Google Cloud.

Orchestrating Inter-Cluster Networking in Kubernetes

How to setup inter-cluster networking between two Kubernetes clusters using Cillium.

Tackling the Challenges of Multi-Cloud for AI Companies

In this blog, I explore the challenges AI companies face when using Kubernetes for optimising GPU usage in Multi-cloud environments and how Ori helps...

How does Ori approach security-by-default?

Ori secures your clouds environments with zero-trust microsegmented networks and secure secret management.

Ori acquires provisioning tool Multy

The acquisition consolidates Ori's leadership position in intelligent application orchestration across distributed clouds.