Rakshith Venkatesh - MinIO Blog

MinIO AIStor with NVIDIA GPUDirect® RDMA for S3-Compatible Storage: Unlocking Performance for AI Factory Workloads

Rakshith Venkatesh Rakshith Venkatesh on | 12 February 2026

In large-scale AI, every watt, core, and microsecond is a competitive edge. GPUs drive the economics of training and inference, making it increasingly important for data paths and faster networks to scale alongside more demanding workloads. NVIDIA has changed the game with GPUDirect RDMA for S3-compatible storage, a breakthrough that preserves the universal S3 API and ecosystem that AI teams

Supercharging Inference for AI Factories: KV Cache Offload as a Memory-Hierarchy Problem

Rakshith Venkatesh Rakshith Venkatesh on | 12 February 2026

Reduce tail-latency spikes from KV cache eviction/recompute, raise effective concurrency per GPU, and improve unit economics (tokens/sec per dollar, cost per token, tokens/sec per watt) while keeping latency predictable under bursty, multi-tenant demand.

Introducing MinIO ExaPOD: The Reference Architecture for Exascale AI

Rakshith Venkatesh Rakshith Venkatesh on AI/ML | 13 November 2025

AI has shifted the baseline for infrastructure, from managing petabytes to operating seamlessly at exabyte scale. Agentic systems, long-context language models, simulation pipelines, and large-scale observability now demand storage architectures purpose-built for this data reality. Today we’re thrilled to announce ExaPOD, MinIO’s validated reference architecture for the exascale era: a one-exabyte, highly dense and efficient building block that

MinIO’s S3 over RDMA Initiative: Setting New Standards in Object Storage for High-Speed AI Data Infrastructure

Rakshith Venkatesh Rakshith Venkatesh on AIStor | 13 November 2024

As the demands of AI and machine learning continue to accelerate, data center networking is evolving rapidly to keep pace. For many enterprises, 400GbE and even 800GbE are becoming standard choices, driven by the need for high-speed, low-latency data transfer for AI workloads that are both data-intensive and time-sensitive. AI models for tasks like large language processing, real-time analytics, and

The MinIO DataPod: A Reference Architecture for Exascale

Rakshith Venkatesh Rakshith Venkatesh on AI/ML | 1 August 2024

The modern enterprise defines itself by its data. This requires a data infrastructure for AI/ML as well as a data infrastructure that is the foundation for a Modern Datalake capable of supporting business intelligence, data analytics, and data science. This is true if they are behind, getting started or using AI for advanced insights. For the foreseeable future, this

Towards Exascale AI Data Infrastructure

Rakshith Venkatesh Rakshith Venkatesh on Cloud Native | 2 April 2024

It's been just over a week for me here at MinIO. The big takeaway from immersing myself in whiteboarding sessions, architecture reviews and customer calls is that the simplicity of the product is both its distinguishing feature and one of its most defining value drivers. This is particularly true at scale. The explosive growth in computing power due

MinIO Blog Posts by Rakshith Venkatesh