arrow_back View All Dates
11:00 • Lightning Talk: Why Your Forecasting Transformer Isn’t Working (And How To Fix It in Python) - Rosheen Naeem, Open Climate Fix
11:15 • Lightning Talk: Deep Learning in the Wild: Embedded PyTorch for Real-World Conservation Bioacoustics - Taraqur Rahman & Owen O'Donnell, OWL Integrations
11:30 • Lightning Talk: How DeepInverse Is Solving Imaging in Science and Healthcare With PyTorch - Andrew Wang, DeepInverse; Minh Hai Nguyen, Université de Toulouse
11:45 • Lightning Talk: ExecuTorch on Microcontrollers: Deploying PyTorch To the Smallest Edge - RJ Ascani & Matthias Cremon, Meta
12:00 • Write Once, Run Everywhere with Pytorch Transformers - Pedro Cuenca, Hugging Face
13:45 • Why WideEP Inference Needs Data-Parallel-Aware Scheduling - Maroon Ayoub, IBM; Tyler Michael Smith, Red Hat
14:15 • The Token Slice: Implementing Preemptive Scheduling Via Chunked Decoding - Maroon Ayoub, IBM & Kellen Swain, Google
14:45 • The Science and Practice of Open and Scalable LLM Evaluations - Grzegorz Chlebus, NVIDIA
15:40 • Enabling State-of-the-art Asynchronous Execution in Torch.compile With CUDA Streams - Michael Lazos, Meta
16:10 • Build PyTorch to Understand PyTorch - Vijay Janapa Reddi, Harvard University; Andrea Mattia Garavagno, University of Genoa
16:40 • Lightning Talk: TerraKit: Standardising AI-Ready Geospatial Data Preparation for the TorchGeo Ecosystem - Rosie Lickorish & Romeo Kienzler, IBM
16:55 • Lightning Talk: Bayesian Neural Networks With Variational Inference in PyTorch - Lars Heyen, Karlsruhe Instute of Technology, Scientific Computing Center
11:00 • Lights, Camera, Inference! Video Generation as a Service With VLLM-Omni - Ricardo Noriega, Red Hat & Doug Smith, Red Hat, Inc
11:30 • Lightning Talk: Coding Agents for Compiler Construction: Beyond the AI Assistant Paradigm - Reza Rahimi, yasp.ai & Stefan Krassin, yasp
11:45 • Lightning Talk: TorchJD: Jacobian Descent in PyTorch - Pierre Quinton, EPFL & Valérian Rey, Simplex Lab
12:00 • Lightning Talk: Ethical, Privacy and Sustainability Considerations in PyTorch Systems - Paula Mesa Macias, Pau&Company
13:45 • Lightning Talk: From Pretrained To Personal: Privacy-First Fine-Tuning on AI PCs - Daniel Holanda Noronha & Iswarya Alex, AMD
14:15 • Sponsored Session: TorchTPU: Expanding TPU Programmability to Pytorch - Kat Ko & Claudio Basile, Google; Jana van Greunen, Meta
14:45 • Lightning Talk: Implementing Single-Dim Strategies With Sharding Validator - Anshul Sinha, Meta
15:00 • Lightning Talk: Jigsaw: Domain and Tensor Parallelism for High-Resolution Input Training - Deifilia Kieckhefen, Karlsruhe Institute of Technology
15:40 • Lightning Talk: Cross-Region Model Serving: PyTorch Inference, Observability & LLMOps - Suraj Muraleedharan, Amazon Web Services
15:55 • Lightning Talk: Running ExecuTorch Applications With Silicon Acceleration, in Ultra-low Power - George Gekov, Arm; Aki Makkonen, Alif Semiconductor
16:10 • On-Device LLM Inference on Android With ExecuTorch and Qualcomm QNN - Shivay Lamba & Kartikey Rawat, Qualcomm
16:40 • Optimizing PyTorch on CPU-GPU Coherent Platforms - Matthias Jouanneaux, Nvidia
11:00 • Lightning Talk: Training Embedding Model Resiliently for Multimodal Model Inference Routing - Huamin Chen, Red Hat & Haichen Zhang, AMD
11:15 • Lightning Talk: Flexible Deployment of PyTorch Models on MCU-Class Devices Using ExecuTorch - Robert Kalmar & Martin Pavella, NXP
11:30 • Why Classic IAM Collapses for Agents: Rethinking IAM for Agentic Systems - Parul Singh, Red Hat
12:00 • Parameterized CUDA Graph Launch in PyTorch: CUDA Graphs Without the Pain - Daniel Galvez, NVIDIA
13:45 • Teaching PyTorch To Read Your Worst PDFs With Docling - Mingxuan Zhao & Peter Staar, IBM & Carol Chen, Red Hat
14:45 • Brevitas Quantization Library - Pablo Monteagudo Lago, AMD
15:40 • torch.compile and Diffusers: A Hands-On Guide to Peak Performance - Sayak Paul, Hugging Face
16:10 • Optimizing Reinforcement Learning at Trillion-Parameter Scale - Songlin Jiang, Aalto University & Mind Lab
16:40 • Securing Agentic AI With PyTorch: Threat Modeling & LLM Red Teaming in Practice - Valeri Milke, VamiSec GmbH
09:00 • Keynote: Co-Evolution: How the Open Source Intelligence Stack Compounds - Mark Collier, Executive Director, PyTorch Foundation, General Manager, AI & Infrastructure, Linux Foundation
09:10 • Keynote: PyTorch Updates - Edward Yang, Research Engineer, Meta
09:35 • Keynote: Community Led Open Source RL - Joe Spisak, VP of Product & Head of Open Source, Reflection AI
09:45 • Sponsored Keynote: From One Node to Distributed Training and Inference. How the PyTorch Ecosystem Changed AI - Ramine Roane, Corporate Vice President of AI Product Management and Ecosystem Development, AMD
09:55 • Keynote: Stream Everything - Moving from Request input to Streaming input - Patrick von Platen, Research Engineer, Mistral AI
10:10 • Sponsored Keynote: Any [ Agent | Model | Accelerator | Cloud ]. Open Source AI Unlocks the World's Potential - Maryam Tahhan, Principal Engineer & Nicolò Lucchesi, Senior Machine Learning Engineer, Red Hat
10:15 • Keynote: The Unbearable Lightness of (Agentic) Evaluations - Besmira Nushi, Senior Manager, AI Research, NVIDIA
11:00 • Helion 1.0: A High-Level DSL for Performance Portable Kernels - Oguz Ulgen, Meta
11:30 • Tour De Force: LLM Inference Optimization From Simple To Sophisticated - Christin Pohl, Microsoft
12:00 • Lightning Talk: Bringing Google’s Colossus to PyTorch: Rapid Storage via fsspec to Keep GPUs Busy - Ankita Luthra & Trinadh Kotturu, Google
12:15 • Lightning Talk: FlexAttention + FlashAttention-4: Fast and Flexible - Driss Guessous, Meta
13:45 • Bringing ExecuTorch To the Next Frontiers of Edge AI - Mergen Nachin, Meta
14:15 • Lightning Talk: Accelerating On-Device ML Inference With ExecuTorch and Arm SME2 - Jason Zhu, Arm
14:30 • Lightning Talk: Combo Kernels: Horizontal Fusion Optimization in Torch.compile - Karthick Panner Selvam, & Elias Ellison, Meta
14:45 • Model-Changing Transforms With Torch.compile - Thomas Viehmann, Lightning AI
15:40 • Lightning Talk: Graph Based Pipeline Parallelism - Sanket Purandare, Meta & Simon Fan, Meta PyTorch
15:55 • Lightning Talk: Beyond Generic Spans: Distributed Tracing for Actionable LLM Observability - Sally O'Malley & Greg Pereira, Red Hat
16:10 • TorchStore: What We Learned Building Distributed Storage Solutions for AysncRL - Lucas Pasqualin, Danielle Pintz, Allen Wang, Amir Afzail Meta
