mlsanityData to 14 Oct 2026

ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Device

arXiv 2605.08195 ↗First posted 5 May 2026cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Local execution of AI on edge devices is important for low latency and offline operation. However, deploying models on diverse hardware remains fragmented, often requiring model conversion or complete reimplementation outside the PyTorch ecosystem where the model was originally authored. We introduce ExecuTorch, a unified PyTorch-native deployment framework for edge AI. ExecuTorch enables seamless deployment of machine learning models across heterogeneous compute environments. It scales from embedded microcontrollers to complex system-on-chips (SoCs) with dedicated accelerators, powering devices ranging from wearables and smartphones to large compute clusters. ExecuTorch preserves PyTorch semantics while allowing customization, support for optimizations like quantization, and pluggable execution "backends". These features together enable fast experimentation, allowing researchers to validate deployment behavior entirely within PyTorch, bridging the gap between research and production.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 11 of its 42 references that are in the map. First posted on arXiv 5 May 2026.

Builds on

11 of 42 references.

References · 11

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  2. 2024SpinQuant: LLM quantization with learned rotationscited by 471
  3. 2014Caffe: Convolutional Architecture for Fast Feature Embeddingcited by 288
  4. 2020TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systemscited by 165
  5. 2023FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterizationcited by 162
  6. 2018CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUscited by 121
  7. 2023MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Trainingcited by 96
  8. 2020MNN: A Universal and Efficient Inference Enginecited by 65
  9. 2021Torch.fx: Practical Program Capture and Transformation for Deep Learning in Pythoncited by 40
  10. 2025TorchAO: PyTorch-Native Training-to-Serving Model Optimizationcited by 26
  11. 2024Local-Global Attention: An Adaptive Mechanism for Multi-Scale Feature Integrationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026A Quantized Native Runtime for On-Device Semantic Audio Generationcited by 0
  2. 2026Meganeura: Portable GPU Training and Inference through Vulkan and Metalcited by 0
  3. 2026vla.simd: Efficient CPU Inference for Language-Conditioned Manipulationcited by 0
  4. 2026Fine-Tuning a 3B-Parameter LLM on a Smartphone: Characterizing Sustained Trainingcited by 0
  5. 2026Linear-Time Non-Local Codec Placement for Machine Learning Model Compressioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026From PyTorch to the NPU: LLM-Agent-Driven Model Conversion Across Heterogeneous Inference Runtimes
  2. 2026Separating Intelligence from Inference: A Standard for Edge-Native AI Computing ↗
  3. 2026KernelGenBench: Can LLMs and Agents Write Efficient Kernels Across Operator Sources and Hardware Platforms?
  4. 2026Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment
  5. 2025Optimizing PyTorch Inference with LLM-Based Multi-Agent Systems
  6. 2026FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution
  7. 2026ExaGEMM: Exploration Framework for CPU-Driven ML Inference via Associative In-Register Computing for Low-Bit GEMM
  8. 2026QEIL v2: Heterogeneous Computing for Edge Intelligence via Roofline-Derived Pareto-Optimal Energy Modeling and Multi-Objective Orchestration