Accelerating on-device ML for Meta’s family of apps with ExecuTorch
Sources: https://engineering.fb.com/2025/07/28/android/executorch-on-device-ml-meta-family-of-apps, engineering.fb.com
ExecuTorch is Meta’s open-source solution for on-device inference on mobile and edge devices, rolled out across Meta’s family of apps (FoA) over the past year. Built in collaboration with industry leaders, it uses PyTorch 2.x technologies to convert models into a stable, compact representation for efficient on-device deployment. Its compact runtime, modularity, and extensibility help developers tailor components for portability across platforms, compatibility with PyTorch, and high performance. Adopting ExecuTorch has helped Meta enhance user experiences across products and services used by billions of people worldwide. Meta’s Engineering blog on ExecuTorch rollout.
More news
First look at the Google Home app powered by Gemini
The Verge reports Google is updating the Google Home app to bring Gemini features, including an Ask Home search bar, a redesigned UI, and Gemini-driven controls for the home.
NVIDIA HGX B200 Reduces Embodied Carbon Emissions Intensity
NVIDIA HGX B200 lowers embodied carbon intensity by 24% vs. HGX H100, while delivering higher AI performance and energy efficiency. This article reviews the PCF-backed improvements, new hardware features, and implications for developers and enterprises.
Shadow Leak shows how ChatGPT agents can exfiltrate Gmail data via prompt injection
Security researchers demonstrated a prompt-injection attack called Shadow Leak that leveraged ChatGPT’s Deep Research to covertly extract data from a Gmail inbox. OpenAI patched the flaw; the case highlights risks of agentic AI.
Predict Extreme Weather in Minutes Without a Supercomputer: Huge Ensembles (HENS)
NVIDIA and Berkeley Lab unveil Huge Ensembles (HENS), an open-source AI tool that forecasts low-likelihood, high-impact weather events using 27,000 years of data, with ready-to-run options.
Scaleway Joins Hugging Face Inference Providers for Serverless, Low-Latency Inference
Scaleway is now a supported Inference Provider on the Hugging Face Hub, enabling serverless inference directly on model pages with JS and Python SDKs. Access popular open-weight models and enjoy scalable, low-latency AI workflows.
Google expands Gemini in Chrome with cross-platform rollout and no membership fee
Gemini AI in Chrome gains access to tabs, history, and Google properties, rolling out to Mac and Windows in the US without a fee, and enabling task automation and Workspace integrations.