AI Performance Engineering Meetup (Munich)

Zoom link: https://us02web.zoom.us/j/82308186562

Talk #0: Introductions and Meetup Updates
by Chris Fregly and Antje Barth

Talk #1: Homa: A Fast Lane for Small Messages
by John Ousterhout, Professor Emeritus of Computer Science at Stanford University

John will explain how Homa can dramatically reduce small-message latency and explore its potential relevance to AI workloads. Drawing on his expertise in transport protocols, he’ll discuss what Homa could offer when small-message latency matters. Its importance for AI workloads remains an open, workload-dependent question.

Bio: John Ousterhout is a Professor Emeritus of Computer Science at Stanford University, the creator of Tcl, and a systems researcher whose current work focuses on the Homa transport protocol.

Zoom link: https://us02web.zoom.us/j/82308186562

Related Links

Github Repo: http://github.com/cfregly/ai-performance-engineering/
O’Reilly Book: https://www.amazon.com/Systems-Performance-Engineering-Optimizing-Algorithms/dp/B0F47689K8/
YouTube: https://www.youtube.com/@AIPerformanceEngineering
Generative AI Free Course on DeepLearning.ai: https://bit.ly/gllm

Monday, November 16, 2026 · 9:00–10:00 AM PST · Online
Zoom link: https://us02web.zoom.us/j/82308186562
Join us for two deep dives into hidden AI performance costs: surprise PyTorch recompilations during inference and compute, memory, and communication bottlenecks in Jev training.
Talk #0: Introductions and Meetup Updates
by Chris Fregly and Antje Barth
Talk #1: The Recompile Ambush: Taming PyTorch Inference Spikes
by Chaim Rand
`torch.compile` can accelerate steady-state inference, yet a guard failure on a new input shape or layout can trigger an expensive recompilation in the request path. Drawing on his latest post, Chaim will compare six approaches using a dynamic graph-neural-network example: cache preloading, bounded recompilation with eager fallback, Dynamo and input-layout tuning, warmup seeding, background compilation, and ahead-of-time compilation with `torch.export` and AOTInductor. He’ll explain their tradeoffs and how the right choice depends on the model, input distribution, runtime environment, and latency requirements.
Bio: Chaim Rand is a machine-learning algorithm developer who writes about PyTorch and practical AI/ML performance optimization.
Based on: Overcoming the PyTorch Recompilation Dilemma in Real-Time Inference Workloads
Talk #2: Follow the Profile: Hunting Jev’s GPU Bottlenecks
by Israel Ogbole, Co-founder and CEO of Zymtrace
Israel will explore the latest Zymtrace/TypeSafe case study on training and serving Jev. He’ll discuss how continuous CPU/GPU profiling and MCP-accessible profile data supported an iterative optimization loop across compute, memory, communication, and inference synchronization. The published case study reports approximately 46% higher training throughput on the same hardware after three successive changes, plus approximately 10% better inference performance after removing a hidden device-to-host synchronization. The talk will focus on how the team found each bottleneck, measured each change, and identified the next constraint.
Bio: Israel Ogbole is co-founder and CEO of Zymtrace, which develops continuous CPU/GPU profiling tools for performance optimization.
Based on: How TypeSafe achieved 46% higher GPU throughput training Jev — with the help of Zymtrace
Zoom link: https://us02web.zoom.us/j/82308186562
Related Links
Github Repo: http://github.com/cfregly/ai-performance-engineering/
O’Reilly Book: https://www.amazon.com/Systems-Performance-Engineering-Optimizing-Algorithms/dp/B0F47689K8/
YouTube: https://www.youtube.com/@AIPerformanceEngineering
Generative AI Free Course on DeepLearning.ai: https://bit.ly/gllm

Monday, November 30, 2026 · 9:00–10:00 AM PST · Online
Zoom link: https://us02web.zoom.us/j/82308186562
A powerful GPU can spend plenty of time waiting. What is it waiting for—and how do you find out?
Talk #0: Welcome and Meetup Updates
by Chris Fregly and Antje Barth
Talk #1: From “Why Is This Slow?” to a Faster Kernel
by Dr. Rajat “Raj” Dandekar, Co-founder of Vizuara
Join Raj for a focused tour of the engineering behind fast AI kernels, drawing on Vizuara’s Kernel Engineering course on Maven. We’ll connect the roofline model to CUDA execution and the GPU memory hierarchy, then look at how profiling guides optimizations such as coalesced memory access, tiling, and tensor-core use. Matrix multiplication and attention provide context for seeing how those ideas fit together in modern AI workloads, including FlashAttention.
The goal is a practical way to decide what to measure, which bottleneck matters, and whether an optimization helped. The session is dedicated to Raj’s talk, with time for audience questions.
Who it’s for: Engineers comfortable with Python or basic PyTorch. Prior CUDA or C++ experience is not required.
Bio: Dr. Rajat Dandekar is a co-founder of Vizuara and a Kernel Engineering course instructor. He holds a PhD in Mechanical Engineering from Purdue University and BTech and MTech degrees from IIT Madras.
Based on: Kernel Engineering: From CUDA Foundations to Frontier AI Kernels
Scheduling note: November 30 is the proposed new date; speaker confirmation is pending.
Zoom link: https://us02web.zoom.us/j/82308186562
Related Links
Github Repo: http://github.com/cfregly/ai-performance-engineering/
O’Reilly Book: https://www.amazon.com/Systems-Performance-Engineering-Optimizing-Algorithms/dp/B0F47689K8/
YouTube: https://www.youtube.com/@AIPerformanceEngineering
Generative AI Free Course on DeepLearning.ai: https://bit.ly/gllm

Zoom link: https://us02web.zoom.us/j/82308186562

Talk #0: Introductions and Meetup Updates
by Chris Fregly and Antje Barth

Talk #1: GPU, PyTorch, and CUDA Performance Optimizations

Talk #2: GPU, PyTorch, and CUDA Performance Optimizations

Zoom link: https://us02web.zoom.us/j/82308186562

Related Links
Github Repo: http://github.com/cfregly/ai-performance-engineering/
O'Reilly Book: https://www.amazon.com/Systems-Performance-Engineering-Optimizing-Algorithms/dp/B0F47689K8/
YouTube: https://www.youtube.com/@AIPerformanceEngineering
Generative AI Free Course on DeepLearning.ai: https://bit.ly/gllm