Executorch: Open-source ondevice AI from @pytorch
@Executorch
Followers
90
Following
51
Media
7
Statuses
32
https://t.co/R5FZH15lNU - end-to-end solution for on-device inference and training
US
Joined March 2024
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 ➡️ https://t.co/1KV3hcsj98
#AI
1
2
14
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
7
21
187
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
Declarative way to run AI models in React Native on device, powered by ExecuTorch. - software-mansion/react-native-executorch
0
1
2
@UnslothAI Thank you @danielhanchen for the great collaboration here!
1
0
1
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
Quantize models to 4-bit with Unsloth and PyTorch to recover accuracy.
1
1
2
🔥 On-Device Audio Generation with ExecuTorch + @StabilityAI | @Arm Demo by Gian Marco Iodice. 🎥 Watch here:
0
1
3
Running Optimized @PyTorch Models on @Cadence DSPs with ExecuTorch We've added support to run ExecuTorch on Tensilica HiFi DSP Family! Check out our blog for more details! https://t.co/VyZMnA0rKI
community.cadence.com
By Vijay Pawar of Cadence and Matthias Cremon of Meta Introduction Deploying PyTorch models on embedded devices, especially audio DSPs, presents unique challenges
0
0
0
https://t.co/XIkqmYLv32
@qualcomm engineers Derrick Johnson and Kartikey Rawat going through running LLMs on-device with Qualcomm Hardware with ExecuTorch
0
0
0
Looking for a react native solution for LLMs?
Announcing React Native ExecuTorch v0.4.0! 🎉 What’s new: 🧠 More LLMs – Integrate a wide range of LLMs into your React Native app 🔧 Tool calling capabilities – Enable LLMs to dynamically interact with APIs & tools 🔍 Text Embedding Models – Transform text into vectors for
0
0
1
ExecuTorch v0.6.0 is now live This release includes: * Significant usability and stability fixes * Windows support * Ready Made Packages for iOS and Android * Native Object-C and Swift APIs * New OpenVino backend The full details here https://t.co/iLlll1uV9w
github.com
We're excited to announce the release of ExecuTorch 0.6! This release builds upon the foundation established in the 0.5 release (January 30, 2025) with significant improvements across various c...
0
0
0
Excited to introduce low-bit operators for Arm CPUs in TorchAO! Seamlessly works across all PyTorch surfaces including eager, torch.compile, AOTI, and ExecuTorch. Check out the details here:
1
3
4
I'm happy to note that with the merge of https://t.co/d7vbKiD6D1, my work on fp16/bf16 GEMV kernels in PyTorch for x86 CPUs without fp16/bf16 hardware support should run out of the box in torchchat on main. It looked good in my tests, but I'm interested in feedback!
github.com
Accounts for: PyTorch changing weight_only default from False to True weights_only default flip for torch.load #1356 Moving from export to export_for_training Use training IR in torchchat expor...
1
5
13
dot com hype all over again. You know when you've been doing things for a while when you start seeing the same patterns return
Driving around SF. Omg this is crazy I can't believe there's billboards advertising cloud GPUs on the streets of SF, the hype is totally out of control. That said, actually I would like some more GPU and I haven't heard of this company yet this looks interesting.
0
0
1
Great work by Software Mansion to enable seamless integration and full offline inference for Llama models in mobile apps.
What if we told you LLaMA 3.2 runs offline in @reactnative with just a few lines of code? 📲🦙 AI integration has never been this easy! Check out the video about our latest, ExecuTorch-powered React Native library 👀 https://t.co/t98ZZpbhgD
0
2
2
🚀 Over 120 innovators across 22 teams are hacking away for the next 2 days, crafting the future of AI-powered on-device solutions with @Meta, @huggingface! Big thanks to #entrepreneurfirst, #scaleway, and @ekimetrics and Shoutout to @juliadenoly, @mergennachin, and many more!
0
0
2
Check out this awesome slide deck by @tarantulae on #PyTorch 2.0 internals (Dynamo, AOTAutograd, Inductor, and more). Packed with lots of details! 🚀 #PyTorch #MachineLearning
https://t.co/W2cmvX9dQe
drive.google.com
0
1
13
Kudos to @kimishpatel from ExecuTorch team in his collaboration with CoreAI team and making this possible. These support safe input/output in lightweight and multimodal applications. Check out the papers here: 1B ➡️ https://t.co/dS9nhiastc Vision ➡️
Following the release of our latest system level safeguards, today we're sharing new research papers outlining work on Llama Guard 3 1B & Llama Guard 3 Vision that support input/output safety on the edge and in multimodal prompts.
0
2
4