Advanced Lessons

PyTorch APIs for High Performance MoE Training and Inference - D. Vega-Myhre; Ke Wen & N. Gimelshein

Sponsored Session: Beyond the Node: Scaling Inference with Cluster-Wide KVCache... - Alon Yariv

Google’s TPU Advantage: Google Cloud VP on Performance & Cost for Gemini

Data and AI Governance - How to Balance Centralization and Decentralization | Amazon Web Services

What is Data Governance - Really? | Amazon Web Services

Dynamic Expert Allocation in GPT 5

How you hear these notes depends on where you’re from #shorts

Master ChatGPT Atlas in One Video

This #Zillow trends expert explains the new ways #Millennials and #GenZ are buying #realestate.

How Zyphra went all-in on AMD + Why Devs feel faster with AI but are slower — with Quentin Anthony

Top Cybersecurity Trends for 2026 | Stay Ahead of Cyber Threats #shorts #simplilearn

Faster R-CNN - Explained!

Lecture 09: Reflections on the Szemeredi-Trotter Theorem

Lecture 19: Random Walks on Finite Groups, Part 3

SRL: NEW AI Training (by Google)

Brené Brown: The Algorithms Have Forced Us Into A Hidden Epidemic, This Is The Only Way Out!

Leveraging PyTorch for Generative AI in Distributed Edge Clouds - Tina Tsou

DeepSpeed: Efficient Training Scalability for Deep Learning - Tunji Ruwase, Snowflake

Lightning Talk: Unlock the Future of Generative AI: TorchTitan's Latest... - Tianyu Liu & Jiani Wang

Sponsored Session: Arctic Inference: Breaking the Speed-Cost Tradeoff in LLM Serving - Aurick Qiao

Efficient MoE Pre-training at Scale on AMD GPUs With TorchTitan -Liz Li & Yanyuan Qin, Matthias Reso

Enabling VLLM V1 on AMD GPUs With Triton - Thomas Parnell, IBM Research & Aleksandr Malyshev, AMD

Sponsored Session: Lightning Talk: Per-iteration PyTorch Visibility... - Shruti Verma & Yi-Ting Wu

Lightning Talk: Vllm-triton-backend: How To Get State-of-the-art Performance on... - B. Ringlein

Sponsored Session: Lightning Talk: PyTorch and Democratization of AI Accelerators - Hong-Seok Kim

Sponsored Session: PyTorch Distributed and Fault Tolerance - Tristan Rice, Meta

Transformers: Standardizing Model Definitions Across the PyTorch Ecosystem - L. Debut & A. Zucker

Enabling Lightweight, High-Performance FSDP With NVIDIA GPU - J. Chang CN, C. Ye, X. Chen & S. Lym

Verl: A Flexible and Efficient RL Framework for LLMs - Hongpeng Guo & Ziheng Jiang, ByteDance Seed

Lifecycle of a Parameter - Philip Bontrager, Meta

Fault Tolerance Training at Pinterest - Chia-Wei Chen & Karthik Anantha Padmanabhan, Pinterest

How Modern PyTorch Supercharges Multimodal Training and Inference at Luma AI - Thomas Neff, Luma AI

Rethinking the Transformer: Toward Native Multimodal Architectures - Bowen Peng, Nous Research

Lightning Talk: Dynamic Shape Recompilations - Bob Ren, Meta

Optimizing Long-Tail and MoE Challenges in Reinforcement Learning with SGLang - Chenyang Zhao, UCLA

AI On-board of Satellites, Towards Autonomous Scientific Instruments - Vit Ruzicka, NASA

Controllable Generation of Synthetic Video Data With Human Motion - Vaclav Knapp

GQA: The speed hack that makes LLMs faster

Absa equips employees with skills to drive migration | Amazon Web Services

Absa and AWS Skills Guild | Africa's first female Golden Jacket winner | Amazon Web Services

Why Grouped Query Attention (GQA) Outperforms Multi-head Attention

AI in the Wild: Lovable | What Happens When Anyone Can Build with AI? | Amazon Web Services

How do I troubleshoot Amazon Q Developer authentication errors in my IDE?

How do I troubleshoot issues when I integrate Amazon RDS for Oracle with Amazon S3?

Lecture 18: Random Walks on Finite Groups, Part 2

Lecture 08: The Szemeredi-Trotter Theorem

Lecture 21: Homogeneous Dynamics, Part 2

How Yoodli trained 15,000 people with Google Cloud Consulting