#rdma

The latest AI and developer news about #rdma, with the original source and a short summary.

MLX Enables Frontier LLM Inference on Mac Studio Clusters via RDMA

A cluster of four M5 Ultra Mac Studios achieves over 36 tokens per second on the 816B-parameter Muse Spark Open model using new RDMA-based distributed inference.

·3·2026.10.15 09:00

Predictive Speculative KV Replication for Bursty LLM Inference

BTB predicts repeated-prefix bursts and proactively replicates KV caches into GPU HBM.

·2026.08.01 04:00

[AI Infrastructure] Network Design Considerations for RoCEv2-based AI GPU Clusters

This covers how to implement lossless Ethernet using RoCEv2 in AI GPU clusters and secure optimal network performance.

·3·2026.07.16 14:00

[AI Infrastructure] The Era of 50,000 GPUs: Success Conditions for AI Infrastructure Businesses

For AI infrastructure businesses to succeed, full-stack optimization capability across GPU, network, and storage is essential.

·1·2026.06.01 11:00

Prefill-as-a-Service: Moving Next-Gen Models' KVCache Across Data Centers

By leveraging the small KVCache of hybrid-attention models, prefill is moved outside the data center.

·1·2026.04.20 09:00

Introducing AWS Interconnect Technology from a Distributed Training Perspective - AWS's Interconnect Foundation Technology, ENI

You need to understand AWS's ENI structure and allocation rules to properly unlock EFA performance.

·1·2026.04.14 12:00

Building an AI Platform: From GPU Adoption to Kubeflow

They transformed manual, legacy AI operations through Kubeflow and GPU optimization.

·1·2025.11.12 20:00