➡️
继续阅读
-
把笔记、微信读书、知乎装进 Obsidian:我基于llm-wiki知识中枢搭建实录
llm-wiki是Andrej Karpathy提出的概念,旨在将个人笔记和博客整合为结构化知识库。通过LLM自动提取和管理信息,用户只需提供知识库结构。...
-
软通动力与头部大模型厂商签署智算服务协议
软通动力与一家大模型厂商在北京签署了智算服务协议,提供Token推理服务,推动智能体时代的产业闭环。协议内容包括大模型推理加速、高性能算力集群优化及行业A...
-
我们需要多少KV缓存预算来支持LLM服务?
在LLM推理集群中,KV缓存的存储预算影响命中率和预填充吞吐量。合理配置KV缓存容量可避免资源浪费和过早驱逐可重用条目。KVCache命中率模拟器帮助用户...
-
Paging Charity! How can engineering leaders avoid becoming Bond villains?
If you want your values to spread throughout the industry, the best thing you...
-
无人谈论的智能代理身份问题
Many agentic projects can sail through development just fine. Then they hit s...
-
LLMs help robots understand vague instructions and focus on key details
To help robots do chores in places like homes and factories, a new approach f...