https://xitter.cf/t.co/R5FZH15lNU - end-to-end solution for on-device inference and training
US
Joined March 2024
- Tweets52
- Following28
- Followers147
- Likes67
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: developer.arm.com/community/…
Executorch: Open-source ondevice AI from @pytorch retweeted
Hardware-Aware AI: Building Agentic Systems from Cloud to Edge with PyTorch, ExecuTorch
AI agents are moving beyond chat interfaces and onto physical devices. In her upcoming session on Hardware-Aware AI at PyTorch Conference North America 2026, Kavya Sri Chennoju from @Arm will demonstrate how PyTorch, ExecuTorch, and Arm Device Connect work together to deploy AI agents safely onto edge hardware such as robot arms and wearables.
Join the open source AI community in San Jose, October 20-21: hubs.la/Q04v4SL60
#PyTorchCon
Executorch: Open-source ondevice AI from @pytorch retweeted
Bring your ideas. We’ll bring the hardware.
Two days to build with open models, on-device inference, and real devices at the ExecuTorch Hackathon—part of Open Source AI Week.
📅 October 17–18 · Founders, Inc., SF
⏳ Project proposals due October 4
Form a team of 3–5, build with @Executorch, and help shape the future of open-source, on-device AI.
🏆 Prizes include Meta AI glasses and Arduino UNO Q boards.
Apply → luma.com/executorch-hackatho…
With @hackersquadio @Meta @Qualcomm @github @fdotinc
#OpenSourceAIWeek #OpenIntelligence
🤖 Made with AI
Executorch: Open-source ondevice AI from @pytorch retweeted
Build AI on the edge with ExecuTorch at a two-day @Meta + @Arm hackathon at San Francisco State University.
Students, developers, and AI enthusiasts can get hands-on experience building AI applications with ExecuTorch on Arm-powered devices, with technical talks, demos, workshops, and mentorship.
Participants will also have the chance to collaborate with fellow builders, showcase their projects to judges from Arm and Meta, and compete for prizes and recognition.
🔗 Learn more and register: arm-executorch.devpost.com/?…
We did it! ExecuTorch team won the Best Industry Paper Award @MLSysConf 2026. Come meet us at the conference next week.
Discord: discord.gg/Dh43CKSAdc
Paper: arxiv.org/abs/2605.08195
Project: github.com/pytorch/executorc…
Schedule: mlsys.org/virtual/2026/calen…
Big congrats to the ExecuTorch team. Their paper just won the Best Industry Paper Award at @MLSysConf 2026. 🏆
ExecuTorch is PyTorch's framework for running models on-device, in production today across phones, wearables, desktops, and embedded systems. Backends include Apple, Arm, Qualcomm, MediaTek, Samsung, NXP, Cadence, Intel, NVIDIA, and others.
Catch the team Tuesday morning in the Best Paper Session ( AM PT) and at the poster session Thursday evening.
Paper: arxiv.org/abs/2605.08195
Discord: discord.gg/Dh43CKSAdc
X: xitter.cf/Executorch
Project: github.com/pytorch/executorc…
Schedule: mlsys.org/virtual/2026/calen…
Executorch: Open-source ondevice AI from @pytorch retweeted
Launching SimCam – a tool that finally lets you test camera features directly in the iOS simulator! 🚀
🎦 Stream video from your Mac's built-in or external camera, inject an image or video, or generate a QR code.
Executorch: Open-source ondevice AI from @pytorch retweeted
🎙️Run Voxtral Realtime locally with ExecuTorch!
💻Thanks to the ExecuTorch team, you can now deploy and run Voxtral Realtime efficiently and fully offline on your MacBook.
ExecuTorch as an external Zephyr module!
You can now use #ExecuTorch in #Zephyr. Together with #Arm, we enabled Zephyr integration and run models on CPU and Arm Ethos-U NPUs with ExecuTorch. Checkout the documentation here: docs.zephyrproject.org/lates…
The #MLX delegate has landed in ExecuTorch(github.com/pytorch/executorc…) and is available on main in OSS. It delivers SOTA GPU performance on #macOS for GenAI models, with 3-6x greater throughput than what was previously possible with #ExecuTorch.
Our paper #ExecuTorch - A Unified PyTorch Solution to Run #ML Models #OnDevice is accepted to appear at #MLSys 2026. Excited!
Executorch: Open-source ondevice AI from @pytorch retweeted
SqueezeSAM on-device, accelerated 🚀
With ExecuTorch and Arm SME2, SqueezeSAM image segmentation achieves up to 3.9× faster inference, reducing FP16 latency from over one second to ~300 ms on a single CPU core.
This makes responsive, interactive on-device AI practical on mobile CPUs, no GPU required, while preserving headroom for richer user experiences.
A strong example of how hardware-aware optimization and operator-level profiling can materially change what’s possible for on-device ML.
🔗 Read the blog: hubs.la/Q040Q9Rq0
👥 Gian Marco Iodice, Damien Dooley, Tyler Mullenbach, Jason Zhu
hashtag#PyTorch hashtag#ExecuTorch hashtag#OnDeviceAI hashtag#OpenSourceAI hashtag#MachineLearning
You can now run TorchAO quantized Gemma-3 models with ExecuTorch on edge devices.
xitter.cf/PyTorch/status/2011872…
TorchAO Quantized Gemma-3 Models Now Available on HuggingFace 🚀
TorchAO quantized Gemma-3 models (4b, 12b and 27b) are now available in multiple quantized formats (FP8, INT4, AWQ-INT4, HQQ-INT8-INT4, QAT-INT4) on HuggingFace Hub! Our models:
* Run efficiently on A100/H100 GPUs (with vLLM) & mobile devices (with ExecuTorch)
* Deliver faster inference, big memory savings, and minimal accuracy loss compared to BF16 model
* Include reproducible quantization recipes for your own models, including algorithms like AWQ, HQQ and QAT
🖇️ Check out the collection: hubs.la/Q03-_LNX0
#LLM #PyTorch #TorchAO #ExecuTorch #VLLM #Quantization #Gemma3 #HuggingFace #EdgeAI
Executorch: Open-source ondevice AI from @pytorch retweeted
Huge thanks to my co-authors @JimmyTYYang1, Jean Ponce, @AdrienBardes, and @ylecun for their guidance 🙏
Special thanks to @garridoq_ and @DanielDugas14 !
Work done at @AIatMeta & @Inria
📄 Paper: arxiv.org/abs/2512.24497
💻 Code + data + checkpoints: github.com/facebookresearch/…
Executorch: Open-source ondevice AI from @pytorch retweeted
Export Ultralytics YOLO11 to ExecuTorch for lightning-fast on-device AI! ⚡
Run YOLO11 directly on mobile and edge devices with optimized performance, low latency, and seamless deployment using Meta’s ExecuTorch runtime.
Learn more ➡️ bit.ly/4ojONZm
#AI #MachineLearning #EdgeAI
Executorch: Open-source ondevice AI from @pytorch retweeted
PyTorch Foundation is heading to NeurIPS 2025 with a full program of workshops, sessions, and community events, including our joint booth with Cloud Native Computing Foundation (CNCF) and the Open Source AI Reception with CNCF, Anyscale, Featherless AI, Hugging Face, and Unsloth AI.
Connect with PyTorch maintainers and ecosystem contributors throughout the conference this week. What to expect:
Workshop: Agentic Development at the Frontier
December 2, 4:00–5:00 PM PT
Featuring Joseph Spisak, Davide Testuggine, Aksel Joonas Reedi, Zach Wentz, Daniel Han, Sanyam Bhutani, and Aakanksha Choudhery
🔗 hubs.la/Q03WkRbY0
Workshop: On Device/Edge AI
December 3, 12:00–1:30 PM PT
Featuring Cagatay Bilgin, Matthias Lecher, Andrey Tovchigrechko, Varun Khare, Vijay Janapa Reddi, Karan Goel, and Mitesh Patel
🔗 hubs.la/Q03WkMNd0
Evening Event: Open Source AI Reception
December 3, 6:00–9:00 PM PT
Hosted by PyTorch Foundation & CNCF with Anyscale, Featherless, Hugging Face, and Unsloth at Union Kitchen and Tap Gaslamp in San Diego
🔗 Register to secure your spot: hubs.la/Q03WkQMR0
Talk: Modular Agents and Orchestrated Coordination using Open Agentic Protocols
December 4, 10:45–10:57 AM PT
Featuring Matt White
🔗 hubs.la/Q03WkQwW0
Booth: Meet with Us in the Exhibit Sponsor Hall
We’re proud to be a Diamond sponsor of NeurIPS 2025 alongside CNCF. Come visit us in the Exhibit Sponsor Hall A/B - Booth #723
#NeurIPS2025 #NeurIPS #OpenSource #OpenSourceAI #PyTorch
Executorch: Open-source ondevice AI from @pytorch retweeted
なるほど
software-mansion/react-native-executorch: Declarative way to run AI models in React Native on device, powered by ExecuTorch. github.com/software-mansion/…
With @UnslothAI and @ExecuTorch, you can fine-tune a model in Unsloth and seamlessly export it to ExecuTorch and deploy it directly on mobile. Check out the blogpost here: docs.unsloth.ai/basics/quant…
Thank you @danielhanchen for the great collaboration here!