庞玉栋博客
//

大数据

161 篇 · 资讯流
  2. arXiv cs.DC（分布式并行）

    EdgeAgent: Orchestrating On-Device LLM inference for End-User Multi-Agent Systems on CPU-GPU Unified Memory Architectures

    Emerging multi-agent LLMs demand privacy-preserving edge deployment, yet current inference systems struggle with these c

    原文 ↗
  3. arXiv cs.DC（分布式并行）

    D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels?

    GPU kernels generated by large language model (LLM) agents can remain less efficient than expert implementations, but ru

    原文 ↗
  4. InfoQ 中国（架构）

    别再给 Agent 一个“毛坯房”了：构建 Agent 拎包入住的开发环境实践｜QCon上海

    点击查看原文>

    原文 ↗
  5. arXiv cs.DC（分布式并行）

    ServeTwin: A Benchmark-Validated Simulator for Distributed LLM Architecture Exploration

    Evaluating distributed LLM serving designs on physical clusters is costly. Yet existing simulators provide only subsets

    原文 ↗
  7. InfoQ 中国（架构）

    生成即合规：Agentic AIGC 驱动的广告素材修复实践｜QCon上海

    点击查看原文>

    原文 ↗
  8. arXiv cs.DB（数据库）

    STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling

    Relational foundation models (RFMs) are pretrained once on a collection of relational databases and prediction tasks, an

    原文 ↗
  9. arXiv cs.DB（数据库）

    HakiCC: LLM-Driven Multi-Agent Design and Optimization of Concurrency Control Protocols

    Large language models (LLMs) have recently been applied in systems research as a tool to reduce human-intensive engineer

    原文 ↗
  10. arXiv cs.DC（分布式并行）

    Leto: Fast In-Place Recovery for LLM Training on Surviving Hardware

    Hardware-operable failures (HOFs) interrupt large language model (LLM) training but permit recovery on the same hardware

    原文 ↗
  12. InfoQ 中国（架构）

    一个忘关的开关，与企业Agent的全栈技术账单

    点击查看原文>

    原文 ↗
  13. InfoQ 中国（架构）

    首发！openJiuwen workSwarm全双工多模态 ，像聊天一样与Agent交互，昇腾算力原生亲和

    点击查看原文>

    原文 ↗