# From PyTorch to the NPU: LLM-Agent-Driven Model Conversion Across Heterogeneous Inference Runtimes

arXiv: https://arxiv.org/abs/2609.27249 · HTML: https://mlsanity.com/paper/2609.27249/

## Key facts

- No citing papers in the map yet (data through 7 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 5 of its 18 references that are in the map.
- First posted on arXiv 23 Sep 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 5 of 5)

- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization](https://mlsanity.com/paper/2511.15915/) (2025)
- [AVO: Agentic Variation Operators for Autonomous Evolutionary Search](https://mlsanity.com/paper/2603.24517/) (2026)
- [From Human Guidance to Autonomy: Agent Skill System for End-to-End LLM Deployment on Spatial NPUs](https://mlsanity.com/paper/2606.07586/) (2026)
- [Xe-Forge: Multi-Stage LLM-Powered Kernel Optimization for Intel GPU](https://mlsanity.com/paper/2605.26118/) (2026)

## Abstract (arXiv)

Edge AI model deployment is a multi-stage engineering process involving model conversion, operator compatibility handling, runtime integration, and precision verification. While prior work has demonstrated agent-based automation for Qualcomm AI Runtime, the broader edge inference runtime ecosystem, including Intel OpenVINO, Rockchip RKNN, NVIDIA TensorRT, and ONNX Runtime, presents distinct toolchains and optimization strategies. This paper extends AIPC (AI Porting Conversion, an LLM agent-driven methodology for AI model deployment automation previously demonstrated on Qualcomm AI Runtime) to multi-runtime scenarios, proposing an LLM agent-driven approach for automated single-model-to-single-runtime deployment across heterogeneous inference backends, such as Intel OpenVINO, Rockchip RKNN, NVIDIA TensorRT, and ONNX Runtime. We decompose the edge AI deployment into standardized, verifiable stages, and inject runtime-specific domain knowledge into the agent execution flow through agent skills, auxiliary scripts, and staged verification loops. Using representative vision models, we demonstrate that agent-based deployment can complete the conversion from a PyTorch model to its executable inference, targeting OpenVINO for x86/NPU, RKNN for RK3588, TensorRT for NVIDIA GPU, and ONNX Runtime for Qualcomm NPU with a focus on FP16 precision deployment feasibility verification. The contributions of this paper primarily lie in providing multi-runtime deployment engineering practice experience, toolchain mapping analysis, a layout-adaptation and inference-replacement layer that removes manual transpose insertion from the agent's repair burden, and an empirical characterization of agent deviation behavior under structured knowledge injection, rather than large-scale systematic benchmarking or cross-runtime operator repair strategy comparison.