ExecuTorch
PyTorch in your pocket
Latest: ExecuTorch 1.1.0 (January 2026); 1.0 GA shipped October 2025
PyTorch's on-device inference runtime for phones, wearables and embedded hardware, announced in 2023 and reaching 1.0 general availability in October 2025 with broad CPU/GPU/NPU backend support (including Arm SME2 via KleidiAI). It lets PyTorch models run efficiently at the edge and underpins on-device AI experiences across Meta's apps and devices.
Why it matters
PyTorch's answer to on-device inference: export a model once and run it on phone CPUs, GPUs and NPUs from Arm, Qualcomm, MediaTek and Apple without leaving the PyTorch ecosystem. It reached 1.0 in October 2025 and underpins on-device AI across Meta's apps and devices, including the quantized Llama 3.2 models.
Facts
- Went from experimental preview (2023) to 1.0 GA (Oct 2025) with hardware partners including Arm, Apple, Qualcomm and MediaTek shipping dedicated backends.
Try it yourself
Documentation ↗ pip install executorch ↗ Code on GitHub ↗
Lineage
Sources
GitHub · executorch ↗PyTorch blog ↗newsroom.arm.com ↗