Rakshith Venkatesh

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

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.

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