Running vLLM on Akash

Learn how to save money by replacing closed-source AI models like GPT-4 by running the leading open-source LLM's on Akash with vLLM.

Brev.dev Leverages Akash Network's Permissionless GPU Infrastructure to Seamlessly Scale

The Rise of Decentralized Compute

Explore the issues in Web2 cloud computing, discover Akash Network's decentralized solution, and learn about adoption barriers in the evolving tech space.

Foundation AI Model Training on Akash

Towards the end of 2023, Overclock Labs (core team behind Akash Network) and ThumperAI (generative AI startup) decided to embark on a mission to train a foundation model on Akash GPUs.

Akash at ETHDenver 2024

Connect with the Akash Core Team at ETHDenver.

Passage Leverages Akash To Launch the First Virtual World on Permissionless GPUs

The demand for decentralized compute is growing fast as total global cloud spending is projected to surpass $1 trillion.

Akash Network and Solve.Care Bring Faster, Cheaper, and More Secure Patient Data Ownership to the Healthcare Industry

Healthcare is a $7.98 trillion industry that impacts every one of us worldwide.

Distributed Machine Learning on Akash Network With Ray

In this post we provide an overview of the challenge of trying to parallelize and scale AI and ML workloads in practice, briefly introduce the best open source framework available and in-use by leading machine learning teams (Ray), talk about why Ray is a great solution for running ML workloads on Akash Network, and provide a reference example and template for those looking to run a Ray cluster on Akash Network’s GPU supercloud.

a/acc: Akash Accelerationism

How strategic progress in 2023 laid the foundation for rapid acceleration in 2024 and beyond.

Akash Network: Q4 2023 Recap

The demand for compute to power large language models (LLMs) and other applications has surged, resulting in record...

Building an SDXL Inference App on the Akash Supercloud

In less than two years, AI diffusion models have improved exponentially

Mainnet 8: GPU Visibility Upgrades

As the proliferation of Large Language Models (LLMs) and AI applications has come to a head, large corporations and agile startups are still struggling to secure access to high-performance GPUs.