2026/9/18 -ExecuTorch v1.2.0 expands on-device AI to more models and more hardware. This release adds real-time speech inference with Voxtral Realtime, promotes Cortex-M ...
2026/8/10 -ExecuTorch Arduino library — run PyTorch models on ARM Cortex-M microcontrollers with CMSIS-NN acceleration. Packaged for Arduino Library Manager.
2026/10/9 -ExecuTorch is PyTorch's open source export and runtime stack for running AI locally on edge devices such as phones, wearables, laptops, browsers, embedded ...
2026/10/30 -Describe the bug A model using torch.complex(real, imag) can be captured with torch.export.export(), but cannot complete the default ExecuTorch export-to-
2026/9/4 -ExecuTorch is PyTorch's on-device runtime that takes a PyTorch model from any domain and deploys it directly onto edge devices without converting to another ...
2026/8/11 -ExecuTorch export and runtime support for Muse Glimmer 30B, including text, vision, DFlash speculative decoding, and OpenAI-compatible serving.
2026/8/10 -ExecuTorch exports directly from the released GGUF checkpoints through its torch.export-based ahead-of-time stack. CUDA export compiles and autotunes Triton ...
3日前 -Example apps and demos using PyTorch's ExecuTorch framework - Releases · meta-pytorch/executorch-examples.
2026/9/11 -Explore how ExecuTorch can partition and optimize one PyTorch model across Arm CPUs, GPUs, and NPUs using five target-specific execution paths. By Ash Naik.
5日前 -Compiler integrations, runtime improvements, and robot-policy experiments. Intel / OpenVINO. Bring Intel hardware optimization into the ExecuTorch deployment.