//
大数据
161 篇 · 资讯流AIGC 驱动的内容生产力变革--Vidu 多模态大模型的创新与实践｜QCon上海
点击查看原文>
原文 ↗Characterizing High Bandwidth Flash for LLM Serving
Large language model (LLM) serving requires substantial memory to store model weights and KV caches. As models grow larg
原文 ↗Agent 不只烧 Token：为什么 Agent Sandbox 正在变得重要？
点击查看原文>
原文 ↗Agent 编程能力从 10% 飙到 70%，Anthropic 新模型却遭遇灵魂拷问：我什么时候才会用它？
点击查看原文>
原文 ↗金句抢先看 | 每天上千万次创建：Agent Sandbox 为什么会成为新算力形态？
点击查看原文>
原文 ↗大模型下沉车规芯片：超六成的车企座舱，为何选中了同一个“端侧大脑”？
点击查看原文>
原文 ↗SPLASH: Switching Parallel Layouts of Attention with Seamless Handoff for LLM Serving
No single way of parallelizing attention serves large language models well under all loads. Low concurrency favors tenso
原文 ↗Janus: Evidence-Before-Effect Sagas and Offline-Verifiable Provenance for Agentic LLMs
Agentic large language models (LLMs) now move money through tools, yet the record of what they did is usually a trace th
原文 ↗自主数据工程：迈向真正智能体成熟度的五个阶段 ｜ 技术趋势
点击查看原文>
原文 ↗Purlin: Separating Orchestration from the Datapath of Collectives
Distributed inference depends on GPU collective communication that must keep pace with evolving hardware and specialized
原文 ↗