Turbocharging AIware: Performance Engineering for Production-Ready FMware
Mon 10 Nov 2025 15:00 - 16:30 at Room 3 - Tutorial (TUT-30) Part 2
This half-day tutorial on Software Performance Engineering for AI-powered Software (AIware) will equip practitioners and researchers with the frameworks, techniques and hands-on insights needed to transform impressive FM/LLM demos into production-ready systems. We will survey transformer decoding fundamentals and model-serving best practices, expose end-to-end performance engineering challenges across the FMware lifecycle, introduce advanced methods such as real-time adaptive routing, and work through a concrete SLA-awareness case study for AI-assisted coding. Participants will leave with actionable patterns and recommendations validated in industrial deployments. The session draws on the presenters’ extensive experience working with FMware systems in both research and real-world settings and prior tutorials at ICSE, FSE and ASE.
Mon 10 NovDisplayed time zone: Eastern Time (US & Canada) change
13:00 - 14:30 | |||
13:00 90mTutorial | Turbocharging AIware: Performance Engineering for Production-Ready FMware 7 Tutorials Haoxiang Zhang Centre for Software Excellence, Huawei Canada, Kishanthan Thangarajah Centre for Software Excellence, Huawei Canada, Kirill Vasilevski Huawei Canada, Arthur Leung , Boyuan Chen Centre for Software Excellence, Huawei Canada, Ahmed E. Hassan Queen’s University |
15:00 - 16:30 | |||
15:00 90mTutorial | Turbocharging AIware: Performance Engineering for Production-Ready FMware 7 Tutorials Haoxiang Zhang Centre for Software Excellence, Huawei Canada, Kishanthan Thangarajah Centre for Software Excellence, Huawei Canada, Kirill Vasilevski Huawei Canada, Arthur Leung , Boyuan Chen Centre for Software Excellence, Huawei Canada, Ahmed E. Hassan Queen’s University |