PulseAugur
中
实时 06:58:05
English(EN) EngineAgent: Agentizing On-Device LLM Inference Engines with Inference Stack Hierarchy Awareness and Hardware Abilities

新型代理实现设备端大模型推理引擎的自动化赋能

作者 PulseAugur 编辑部 · [1 个来源] ·

研究人员开发了EngineAgent，一个旨在自动化大语言模型（LLM）设备端推理过程的系统。EngineAgent通过将通用引擎和硬件知识与模型特定的实现分离开来，解决了LLM适配多样化移动硬件的复杂性。这种方法能够更有效地协调转换、图构建和后端执行过程中的变更，与现有的编码代理相比，提高了模型赋能的成功率并减少了调试时间。 AI

影响 简化了LLM在多样化移动硬件上的部署，可能加速设备端AI能力的普及。

排序理由 该集群包含一篇描述LLM推理新系统的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新型代理实现设备端大模型推理引擎的自动化赋能

本文如何被排名

Signal score
36 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇描述LLM推理新系统的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
infra, paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Zhengxiang Huang, Yujie Sun, Shengheng Chen, Zhaode Wang, Chaoyue Niu, Zeyu Zhao, Chengfei Lv, Fan Wu, Guihai Chen ·

    EngineAgent：具有推理栈层级感知和硬件能力的原设备大语言模型推理引擎的Agent化

    arXiv:2611.14356v1 Announce Type: cross Abstract: Rapidly evolving LLM architectures and heterogeneous mobile hardware make supporting new models in on-device inference engines a recurring and costly system challenge. Each model may require coordinated changes across conversion, …

相关实体

相关话题