arXiv cs.AI· Zhanwei Wu (Qualcomm Technologies, Inc), Jianhao Su (Qualcomm Technologies, Inc), Brian Zhang (Qualcomm Technologies, Inc), ShengTing Huang (Qualcomm Technologies, Inc), Weidong Feng (Qualcomm Technologies, Inc), Gang Liu (Qualcomm Technologies, Inc), Zhiguo Li (Qualcomm Technologies, Inc), Wei Huang (Qualcomm Technologies, Inc), Li Tan (Qualcomm Technologies, Inc), Wanjun Li (Qualcomm Technologies, Inc), Zejiong Teng (Qualcomm Technologies, Inc), Changgeng Zhong (Qualcomm Technologies, Inc), Guanping Wu (Qualcomm Technologies, Inc), Han-Hsing Tu (Independent Researcher)·· 3 小时前AI 评分38
Qualcomm 提出 AIPC：基于证据引导的智能体工作流用于 PyTorch 项目部署
AIPC: Evidence-Guided Agent Workflows for PyTorch Project Deployment
AI 导读
Qualcomm 团队提出 AIPC（AI Porting & Conversion），一种面向 PyTorch 推理项目部署到端侧 NPU 的智能体方法，结合结构化 Skills 与工具链、运行时和性能分析证据进行跨层诊断与修复。
正文 · 原文
Authors:Zhanwei Wu (1), Jianhao Su (1), Brian Zhang (1), ShengTing Huang (1), Weidong Feng (1), Gang Liu (1), Zhiguo Li (1), Wei Huang (1), Li Tan (1), Wanjun Li (1), Zejiong Teng (1), Changgeng Zhong (1), Guanping Wu (1), Han-Hsing Tu (2) ((1) Qualcomm Technologies, Inc., (2) Independent Researcher)
Abstract:Deploying and optimizing a PyTorch inference project on a dedicated accelerator, especially an on-device NPU, requires more than using a framework device API as with CUDA. The project must be converted into hardware-runtime artifacts and adapted to the target toolchain and application interface. Differences in model formats, quantization flows, operator support, and toolchain interfaces create cross-layer problems spanning PyTorch/ONNX models, toolchains, runtimes, and device execution. LLM Agents can invoke tools to address such problems, but may drift because of insufficient domain knowledge, large configuration and repair spaces, or poor path selection.
We propose AIPC (AI Porting & Conversion), an Agent method for deploying PyTorch inference projects. AIPC combines structured Skills with toolchain, runtime, and profiling evidence to drive cross-layer diagnosis and repair, organizing model adaptation, artifact building, on-target execution, accuracy repair, and performance optimization into one deployment flow. We evaluate AIPC on the on-device NPU path of Qualcomm QAIRT across vision, speech, LLM, and diffusion models. In two optimization cases, 6/7 Skill-arm Whisper-Small runs meet predefined accuracy and latency criteria versus 0/6 control runs, while YOLO-Worldv2 achieves a 2.791x end-to-end speedup versus 1.599x for the control. Under a pre-fixed deployment contract, Skill, tool permissions, and check conditions, some runs achieve zero in-run human intervention (0-HITL). We also examine Qwen3.8-27B as a locally deployable model for driving an Agent workflow.
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.34890 [cs.SE] |
| (or arXiv:2610.34890v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34890 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jianhao Su [view email]
[v1]
Mon, 26 Oct 2026 06:10:01 UTC (24 KB)
来源：arXiv cs.AI · arxiv.org