跳到正文
arXiv · 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)·· 24 天前AI 评分20

AIPC:用于 PyTorch 项目部署的证据引导智能体工作流

AIPC: Evidence-Guided Agent Workflows for PyTorch Project Deployment

AI 导读

AIPC 结合结构化 Skills 与工具链证据,实现 PyTorch 项目在高通 NPU 上的自动部署与优化。 在两个优化案例中,Whisper-Small 有 6/7 次运行达标(对照组 0/6),YOLO-Worldv2 实现 2.791 倍端到端加速(对照组 1.599 倍),部分运行无需人工干预。 该方法将模型适配、构建、执行、精度修复与性能优化整合为单一部署流程。

来源:arXiv · AI · arxiv.org