ExecuTorch now builds on Snapdragon X Elite laptops; two paths to on-device LLM inference
carrycooldude · x · 2026-10-22
PyTorch's ExecuTorch can now be built on Windows-powered Snapdragon X Elite laptops, opening local AI development on accelerated PC hardware. The author outlines two on-device inference paths:
- ExecuTorch: if you have a PyTorch model, bring it to on-device inference; the current demo runs on CPU.
- GenieX: GGUF models can run via GenieX with selectable backends — NPU, GPU, or CPU — depending on your setup.
He demoed Llama 3.2 1B running locally on a Samsung Galaxy S25 Ultra. Rule of thumb: PyTorch models → ExecuTorch, GGUF models → GenieX.
More from Infra
- Google and Meta open-source TorchTPU, bringing native PyTorch support to TPUs — PyTorch · 2026-10-22
- NVIDIA keynote: silicon photonics CPO switches hit 102.4 Tb/s, Vera Rubin architecture unveiled — thealexbanks · 2026-10-22
- PyTorch Foundation Adds Nine Members, Nebius, Nscale and Shopify Join as Platinum — PyTorch · 2026-10-22
- GPU startup Flappy Airplanes raises $1B Series A co-led by Index and Lux — vitaliychiley · 2026-10-22
- Crusoe unveils Tinker API-compatible LLM post-training platform at PyTorch Conference — PyTorch · 2026-10-22
- Open PR optimizes DeepSeek-V4.1 inference on RTX PRO 6000 Blackwell — AlpinDale · 2026-10-22