AI

Scaling KV Caches for LLMs: How LMCache + NIXL Handle Network and Storage...- J. Jiang & M. Khazraee

Serving PyTorch LLMs at Scale: Disaggregated Inference With Kubernetes and Llm-d

M. Ayoub & C. Liu

SPDX: Tackling System Risk in Modern Supply Chains

Kate Stewart & Gary O'Neall

Sponsor Build AI Anywhere with ROCm™ Software: AMD and PyTorch Bring...

Anush Elangovan

Sponsor Session: Low-Precision Inference without Quality Loss...

Pankaj Gupta & Philip Kiely

Sponsored From Transactions to Transformers: Hardware Built for...

Christian Jacobi

Sponsored Unlocking AI at Scale for PyTorch Developers

Jeff Gehlhaar

The Building Blocks of Agentic Al

Joe Spisak, Product Director, Meta Superintelligence Labs

The Building Blocks of Today’s and Tomorrow’s Language Models

Sebastian Raschka, RAIR Lab

The Future Is Tiled: Using CuTile & TileIR To Write Portable, High-performance GPU...- Jared Roesch

The OpenMDW License Agreement: Simple, Permissive Terms for AI Model Materials

Steve Winslow

The Physical Turing Test: Solving General Purpose Robotics

Jim Fan, NVIDIA

Thunder: Distribute and Optimize Your PyTorch Models With Zero...

Luca Antiga & Thomas Viehmann

Towards Building Safe and Secure Agentic AI

Dawn Song, UC Berkeley

Transformers: Standardizing Model Definitions Across the PyTorch Ecosystem

L. Debut & A. Zucker

Unlock the Future of Generative AI: TorchTitan's Latest...

Tianyu Liu & Jiani Wang

Unlocking Performance: Harnessing LLMs To Streamline GPU Kernel Development in...

Jiannan Wang

Verl: A Flexible and Efficient RL Framework for LLMs

Hongpeng Guo & Ziheng Jiang, ByteDance Seed

vLLM & Deepspeed Updates

Simon Mo & Tunji Ruwase

Vllm-triton-backend: How To Get State-of-the-art Performance on...

B. Ringlein

vLLM: Easy, Fast, and Cheap LLM Serving for Everyone

Simon Mo, vLLM

Welcome & Opening Remarks

Matt White, Executive Director, PyTorch Foundation

Welcome Back

Matt White, with Special Guest Joe Spisak, Meta

Welcome Back to Day 2

Matt White, Executive Director, PyTorch Foundation

What's New in Torch.onnx

Maanav Dalal & Justin Chu, Microsoft

A Practical Field Guide to Optimizing Cost, Speed & Accuracy of LLMs

Niels Bantilan, Union.ai

A Practical Framework for Reliability and Performance

Irena Grabovitch-Zuyev, PagerDuty

A Practical Guide to Fine-Tuning and Deploying Vision Models

Zac Carrico, Apella