Blogs

As generative AI becomes more efficient, large language models (LLMs) are likewise shrinking in size. This creates new opportunities to run LLMs on more efficient hardware, on cloud machines doing AI inference…

In this blog post, learn how the Arm Developer Advocacy team is exploring how machine learning can enable a sign-to-speech translator for video conferencing.

With the recent Arm SME2 announcement, the role of Arm KleidiAI is increasingly clear as Arm’s AI accelerator layer powering the next wave of AI.

Laying the foundation for neural upscaling to enable sharper, smoother, AI-powered gaming on next-generation Arm GPUs.

A deep dive into a practical, ML-powered approach to temporal super sampling.

We are thrilled to announce our collaboration with Unity on the release of the new Unity Profiler eBook for Unity6. The eBook is a comprehensive guide to optimizing performance across many platforms and…

Led a hands-on Yellow Teaming workshop at WeAreDevelopers, exploring Responsible AI and LLMs on Arm-powered tech.

Build safe, modular SDV systems on Arm with functional safety, containerized workloads, and DDS-based real-time communication.

This blog explores how Zilliz Cloud migrated from x86 to Arm CPUs to boost performance and slash costs with Arm Neoverse CPUs for compute-intensive AI workloads, scalable vector search and RAG pipelines…

Arm energized KubeCon + CloudNativeCon China 2025, driving record dev engagement and showcasing cloud-native AI innovation on Arm-based infrastructure.

Arm Development Studio 2025.0 now available with Arm Toolchain for Embedded Professional.

Metis uses AI to detect design flaws and logic bugs missed by traditional tools, helping teams build secure software with context-aware reviews.

In this blog, we introduce the new sparse functions added in Arm Performance Libraries 25.07. We also take a closer look at new features and share performance insights based on benchmarks running on Arm…

A year of Arm KleidiAI in XNNPack brings major ML performance boosts—no code changes needed. Transparent, seamless acceleration on Arm CPUs.

Build next-gen mobile AI apps with SME2—no code changes needed. Accelerate performance across devices using top AI frameworks and runtimes.

Exploring advanced mobile GPU optimizations in Godot using Arm tools like Streamline and Mali Offline Compiler for real-world performance gains.

Migrating to Arm-based AWS Graviton3 improved SiteMana’s scalability, latency, and costs while enabling real-time ML inference at scale.

Run consistent latency and bandwidth checks on CMN interconnects using AMBA Viz’s new performance script—no API expertise needed.

Learn how senior engineers can coach AI coding agents to design, debug, and deliver high-quality code in immersive dev environments.

Boosted Llama.cpp Q6\_K & Q4\_K inference using Arm's I8MM (smmla) for faster, efficient int8 matrix multiplies on Neoverse-N2 CPUs.

GCC 15 brings major Arm optimizations: enhanced vectorization, FP8 support, Neoverse tuning, and 3–5% performance gains on SPEC CPU 2017.