PyTorch Day Japan 2026 comes to Tokyo on December 10, and the call for proposals is officially OPEN! We're accepting proposals for session presentations and Lightning Talks across the full spectrum of open source AI, PyTorch, and AI/ML. Suggested topics include: 🚀 Sovereign AI (Local & Open Models) 🏋️ Physical AI & Edge AI 💡 PyTorch Ecosystem Submit a Proposal by September 27 at 11:59 pm JST >>

PyTorch conferences are the open source AI community’s town square, where what’s next gets decided. At #PyTorchCon# NA 2026, Core PyTorch sessions focus on the framework itself and the engineering work shaping how it is built and extended. The program spans torch.compile and dynamic shapes, distributed communication, out-of-tree backends, the release process and CI, profiling and observability, tensor layouts, stable ABI, and accelerator backends. Featured speakers include: @AMD: Prachi Gupta @awscloud Annapurna Labs: Esha Lakhotia @Google: Claudio Basile @Huawei: Jiahao Chen and Jiahao Tan @IBM: Olivier Tardieu and Dave Grove @IBMResearch: Matthew Arnold, Antoni Viros i Martin, and Avery Blanchard @intel: Yu Guangye, Eikan Wang, Panos Kourdis, and Tanima Dey @Meta: Andrey Talman, @drisspg, @rice_fry, Kapil Sharma, Natalia Gimelshein, William Wen, Steven Troxler, @__avik, @sanketpurandare, @aditvenk, Elias Ellison, @janeyx99, Simon Layton, Laith Sakka, Angel Li, Richard Zou, and Yidi Wu @nvidia: @memorypaladin, Sreeram Potluri, and Artem Polyakov @RedHat: Subin George Malana, Jewel K M, Sean McGovern, and Christopher Leonard @amazon: Pinak Panigrahi Register by September 4 to save: Read the Core PyTorch session guide:

PyTorch 2.13 is here, with 3,328 commits from 526 contributors and updates across FlexAttention, CuTeDSL, nn.LinearCrossEntropyLoss, torchcomms, FSDP2, Python 3.15 wheels, ROCm, Arm, and XPU. The release blog and notes cover FlexAttention on Apple Silicon with up to ~12x speedup over SDPA on sparse patterns, a deterministic backward path on CUDA, the CuTeDSL "Native DSL" backend for Inductor, nn.LinearCrossEntropyLoss to reduce peak GPU memory by up to 4x, torchcomms for large-cluster training, and FSDP2 communication overlap improvements. On July 22 at 11 a.m. PT, join @albanDesmaison (@Meta), Andrey Talman (@Meta), Piotr Bialecki (@NVIDIA), and Chris Gottbrath for a live 2.13 Q&A. 🔗 Read the release blog, and register for the live Q&A:

PyTorch Foundation supported the ExecuTorch Hackathon in San Francisco, where more than 100 participants across 20+ teams built real-time AI applications using PyTorch and ExecuTorch. Teams built on Snapdragon-powered Samsung Electronics Galaxy S25 Ultra devices, focusing on latency, offline capability, privacy-sensitive processing, energy efficiency, and real-time user experience. Congratulations to the winning teams: 1st Place: SafeScreen AI, an on-device visual safety layer 2nd Place: SixthSense, an assistive wearable that converts visual information into directional haptic signals 3rd Place: Toddle AI, a privacy-first prototype for analyzing toddler walking patterns locally The winning projects showed how local execution can support applications that require immediate feedback, limited connectivity, or sensitive data processing. Read the full recap from @matthew_d_white (PyTorch Foundation), Andrew Caples (@Meta), and Lauren Lunde (@Qualcomm):

PyTorch Foundation is a Gold Sponsor of Agentic AI Summit 2026. Matt White, CTO of PyTorch Foundation, will lead “The Open Agentic Stack,” on building AI systems with open source, open standards, and composability. 🔗

PyTorch-native NeMo AutoModel handles transformer pretraining in @nvidia's end-to-end workflow for building a transaction foundation model. The workflow combines GPU-accelerated data processing and tokenization, decoder-only model pretraining, embedding extraction, and XGBoost fraud classification. On the synthetic @IBM TabFormer dataset, combining raw features with learned embeddings increased Average Precision by 41.76% over the raw-feature baseline. 🔗 Read the full post:

At PyTorch Conference North America 2026, Nicolò Lucchesi, Research Engineer at @MistralAI and vLLM maintainer, will present joint work with @AWS and @RedHat on how disaggregated serving in vLLM has evolved to support the latest generation of hybrid models. This session will cover the evolution of disaggregated serving for modern hybrid architectures, protocol developments aimed at reducing end-to-end latency, and new key-value pinning mechanisms designed for reliability at scale. Join us in San Jose on October 20-21: #PyTorchCon# @vllm_project

The PyTorch Korea User Group will host its inaugural offline conference on Saturday, November 21, 2026, hosted at AWS Korea in Centerfield East, Seoul. Designed around the end-to-end AI lifecycle, the event features three primary tracks: Build, Serve, and Run. Community members, developers, and researchers are invited to submit session proposals highlighting real-world project wins, takeaways from failed experiments, or core performance optimizations. The deadline to submit proposals is Sunday, September 13, 2026, at 23:59 KST. Submit your talk today:

At PyTorch Conference North America, Ricardo Noriega de Soto, Tech Lead for the vLLM Omni team and Alexander Brooks, Principal Machine Learning Engineer @RedHat, will demonstrate how extending vLLM’s prefix caching mechanism to multistage pipelines boosts inference speeds while reducing GPU memory overhead. Join us in San Jose on October 20th to learn practical strategies for optimizing complex AI workloads: #PyTorchCon# @vllm_project

At PyTorch Conference North America 2026, hear directly from and connect with the people working on PyTorch, @vllm_project, @DeepSpeedAI, @raydistributed, Helion, and Safetensors, alongside experts working across the AI stack. At #PyTorchCon# NA 2025, Christian Jacobi (@IBM) spoke about clients thinking about deploying AI across core IT and business processes and what comes next: “There’s a lot of innovation ahead of us to do that at scale with the qualities of service that they are used to from classical enterprise computing.” PyTorch conferences are the open source AI community’s town square, where what’s next gets decided. Register by September 4 to save on your conference pass: #PyTorchCon#