AMD and Cohere connect AI to enterprise knowledge with private search and retrieval, supporting data control and evolving AI workflows
November 19, 2026
AMD XDNA™ 2 brings the world’s first NPU support to Unsloth Desktop. Unlock 100+ agentic apps with local AI inference powered by Lemonade and FLM.
After consolidating data, the next test is whether enterprise data infrastructure is ready for a big increase in requests from at-scale agentic AI.
November 18, 2026
AMD Instinct MI350P brings AI inference to Windows Server with simplified deployment, flexible GPU partitioning and control over enterprise data
November 17, 2026
AMD and RGS simplify HPC and AI on Kubernetes with a hardened reference architecture for efficient GPU scheduling and utilization.
November 16, 2026
See how AMD AI NIC™ technology serves AI for Science, running AI training and MPI simulations on one Ethernet network with AMD Instinct™ MI355X GPUs.
See how AMD Instinct™ GPUs deliver faster training and broader coverage in MLPerf® Training 6.1, with generational and round-over-round gains.
AMD and HiddenLayer combine high-performance compute and AI security to help enterprises protect data, manage risk and scale AI adoption
Discover how AOCL 6.0.0 optimizes 6th Gen AMD EPYC™ CPUs.
FastFlow v1.0.13 adds a high-performance GPU flow, powered by HIP EP, alongside its NPU flow.
Explore ROCm 10.2.0, featuring refreshed frameworks, enhanced memory and library capabilities, and more as AMD advances the developer experience
Learn how ATOM keeps AgentX coding sessions warm on AMD Instinct™ MI355X GPUs, from prefix and state reuse to prefill scheduling and fused decode kern…
Learn how an AITER pin keyed by kernel text beats Inductor's default glue config, and how it compares with open-list autotune.
See how IBM’s Pelagos decoder and AMD Instinct GPUs accelerate quantum error correction simulations, scaling throughput 6.23× from one to eight GPUs.
Learn how to reproduce AMD's MLPerf Training v6.1 submission result.
November 15, 2026
In this blog, we share the technical details of how we accomplish the results in our MLPerf Training v6.1 submission.