Join us: Optimizing AI Workloads on Arm: Live Code-Along session 4 November 2026

What is limiting the performance of your AI inference workloads, and how can profiling data help you identify where to optimize?

Join our upcoming Arm Code-Along to explore an end-to-end performance optimization workflow using Arm Performix and llama.cpp.

During the session, we will demonstrate how to:

• Run llama-bench with a 2.5-billion-parameter model to establish a performance baseline.
• Profile the workload using Arm Performix and identify bottlenecks with LLM-assisted analysis.
• Use profiling evidence to guide a targeted code optimization.
• Validate improvements through repeatable benchmarking and before-and-after comparisons.

The session will also include a live Q&A with Arm experts.

Date: Wednesday 4 November 2026

Time: 9 a.m. PST | 5 p.m. GMT | 6 p.m. CET

Duration: 45 minutes + Q&A

Register here: https://developer.arm.com/code-along/optimizing-ai-workloads-on-arm