PyTorch✓

Alan Zhu @alanzhuly

We brought two things to @PyTorch Conference. At the @Qualcomm booth, we demoed GenieX, the open-source Gen AI runtime my team builds, running @liquidai's LFM-VL on @Innodisk_Corp's Dragonwing IQ9. It watched a live camera feed and described what it saw, all on the device. Multimodal is the workload moving on-device in production. Small VLMs are good enough now for most of what a camera needs to understand, and you don't pay per frame or wait on the network. We also ran a hands-on workshop with @awscloud : fine-tune on SageMaker, then run the model locally with GenieX. Most questions were some version of "how do I get my own model running on my own hardware?" That's sovereign AI at developer scale, and it's exactly what GenieX is for.

Executorch: Open-source ondevice AI from @pytorch @Executorch

This is how we bring AI inference to microcontrollers, without the complexity of switching frameworks. The new @Executorch Cortex-M backend uses @Arm CMSIS-NN to accelerate @PyTorch models on Arm Cortex-M CPUs. Take a look at the report here:

Amazon Science @AmazonScience

TorchNeuron is now open source. Our new @PyTorch backend translates code into operations executable on AWS Trainium with minimal or no code changes. Learn how the team used AI agents and hundreds of thousands of models to validate it:

Intel Devs @inteldevs

Intel and AMD are working together to simplify AI development on x86. By bringing @PyTorch CPU optimizations together through oneDNN, we’re creating a more consistent software path for developers across Intel and AMD processors. Learn more:

Google Cloud Tech @GoogleCloudTech

Big day for the @PyTorch ecosystem at #PyTorchConf2026 🚀 We’re officially open-sourcing TorchTPU—enabling native, hardware-accelerated PyTorch execution across Cloud TPUs and custom infrastructure. Here’s everything we launched to supercharge your training & inference workloads 🧵👇

Intel Devs @inteldevs

Your AI workflows shouldn't be tied to your desk. With AI Playground Home Agent and Slack/Telegram, you can launch @PyTorch-powered image generation and content creation from your phone while the compute stays local on your Intel-powered AI PC. See it in action at PyTorch Conference or:

CNCF @CloudNativeFdn

The collaboration between deep learning teams and cloud native engineers doesn't stop when the expo floor closes. We're wrapping up two great days at @PyTorch Conference North America and taking these shared insights straight into KubeCon + CloudNativeCon. Register for KubeCon + CloudNativeCon North America:

Techstrong.ai @Techstrongai

PyTorch sits at the heart of AI development and is increasingly the software layer through which hardware vendors compete for workloads, and this year's conference showed that plainly, with Google's TorchTPU and Amazon's TorchNeuron adding native backends that port existing PyTorch work onto their own accelerators. Behind the common modeling interface, though, the kernels, compilers and low-level system software are still fragmented, and with more than 600,000 GitHub projects and roughly 150 pull requests a day, success is straining the maintainers as much as it is propelling the ecosystem. Read the full report on the state of PyTorch and the case that its open future is already here: #PyTorch #AI #OpenSource #MachineLearning #LLM