#executorch

PyTorch

@pytorch.org

21 hours ago

#ExecuTorch addresses fragmented native deployment for #AI agents as a #PyTorch native platform. It enables voice models across CPU, GPU, and NPU on Android, iOS, Linux, macOS & Windows

🔗 pytorch.org/blog/building-voice-agen...

Miss Kitty 🌈🌈🌈

@misskitty.art

2 weeks ago

Modern #Androids pack 45+ #TOPS of #NPU compute. Instead of draining battery, a native app using #ExecuTorch and #NNAPI runs 4-bit quantized #LLMs natively, turning smartphones into a massive, parallelized compute swarm. 🧠🔋 #EdgeAI #MachineLearning #AndroidDev

Edoardo Vacchi

@evacchi.dev

1 month ago

TIL #executorch for embedded inference 😍

Ed Miller

@bluevalhalla.bsky.social

3 months ago

If you are interested in running #PyTorch models on the latest Arm compute using #ExecuTorch, don't miss this!

Kiyoshi Araki

@cupid2417.bsky.social

4 months ago

Optimizing AI for Mobile: The Power of Model Quantization (3) Part 3: Quantizing and Evaluating Speech Models with Executorch

Following up on my previous post, this is the third installment in my series on on-device AI benchmarks.

medium.com/@cupid20103/...

#ai #on_device_ai #timit #executorch #quantization #hugging_face #python #pytorch

Kiyoshi Araki

@cupid2417.bsky.social

4 months ago

Optimizing AI for Mobile: The Power of Model Quantization (2) Part 2: Choosing the Right Quantization Method for Real-World Models

Following up on my previous post, this is the second installment in my series on on-device AI benchmarks.

medium.com/@cupid20103/...

#ai #on_device_ai #onnx #executorch #quantization #hugging_face

Thiard News@F4F

@newsen.bsky.social

4 months ago

Alif Semiconductor Advances Edge AI with ExecuTorch Runtime for MCUs Alif Semiconductor has introduced ExecuTorch Runtime support to its Ensemble MCUs, enhancing generative AI capabilities for edge devices, enabling local inference.

Alif Semiconductor Advances Edge AI with ExecuTorch Runtime for MCUs #United_States #San_Francisco #Edge_AI #Alif_Semiconductor #ExecuTorch

embedded.com

@embedded-online.bsky.social

4 months ago

Arm and Meta Bring AI Everywhere with ExecuTorch 1.0 General Availability Imagine AI assistants that work privately on your device, voice interfaces that respond instantly without cloud access, or games that adapt in real-time to every player. With the general availability (GA) release of ExecuTorch 1.0, Meta’s on-device runtime for PyTorch, in partnership with Arm, this vision of seamless, low-latency, energy-efficient AI running across billions of edge devices is now a practical reality.

Arm and Meta Bring #AI Everywhere with #ExecuTorch 1.0 General Availability