Search papers, labs, and topics across Lattice.
This paper introduces AIPC, an AI agent-driven system for automating the deployment of AI models to hardware-specific inference runtimes, focusing on Qualcomm AI Runtime (QAIRT). AIPC decomposes the deployment process into standardized stages, leveraging Agent Skills and a validation loop to inject domain knowledge and ensure correctness. Experiments show AIPC can deploy vision models from PyTorch to runnable QNN/SNPE inference in 7-20 minutes, significantly reducing deployment time and expertise requirements.
Automating AI model deployment to Qualcomm hardware is now 10x faster and cheaper thanks to an AI agent that handles the messy details of quantization, operator compatibility, and runtime integration.
Edge AI model deployment is a multi-stage engineering process involving model conversion, operator compatibility handling, quantization calibration, runtime integration, and accuracy validation. In practice, this workflow is long, failure-prone, and heavily dependent on deployment expertise, particularly when targeting hardware-specific inference runtimes. This technical report presents AIPC (AI Porting Conversion), an AI agent-driven approach for constrained automation of AI model deployment. AIPC decomposes deployment into standardized, verifiable stages and injects deployment-domain knowledge into agent execution through Agent Skills, helper scripts, and a stage-wise validation loop. This design reduces both the expertise barrier and the engineering time required for hardware deployment. Using Qualcomm AI Runtime (QAIRT) as the primary scenario, this report examines automated deployment across representative vision, multimodal, and speech models. In the cases covered here, AIPC can complete deployment from PyTorch to runnable QNN/SNPE inference within 7-20 minutes for structurally regular vision models, with indicative API costs roughly in the range of USD 0.7-10. For more complex models involving less-supported operators, dynamic shapes, or autoregressive decoding structures, fully automated deployment may still require further advances, but AIPC already provides practical support for execution, failure localization, and bounded repair.
