GEOZ

标签:DeepSeek

查看包含 DeepSeek 标签的所有文章。

141
VAC记忆系统在LoCoMo 2025基准测试中准确率如何达到80.1%?

VAC记忆系统在LoCoMo 2025基准测试中准确率如何达到80.1%?

BLUF
VAC Memory System is an open-source conversational memory framework for LLM agents that achieved 80.1% accuracy on the LoCoMo 2025 benchmark through a hybrid retrieval architecture combining MCA gating, FAISS semantic search, BM25 lexical search, and cross-encoder reranking. 原文翻译: VAC记忆系统是一个开源的大语言模型智能体对话记忆框架,通过结合MCA门控、FAISS语义搜索、BM25词法搜索和交叉编码器重排序的混合检索架构,在LoCoMo 2025基准测试中实现了80.1%的准确率。
AI大模型2026/4/10
KTransformers框架如何通过CPU-GPU异构计算优化LLM推理与微调?

KTransformers框架如何通过CPU-GPU异构计算优化LLM推理与微调?

BLUF
KTransformers is a flexible framework for optimizing large language model inference and fine-tuning through CPU-GPU heterogeneous computing, featuring two core modules: kt-kernel for high-performance inference and kt-sft for efficient fine-tuning. 原文翻译: KTransformers是一个通过CPU-GPU异构计算优化大语言模型推理与微调的灵活框架,包含两个核心模块:kt-kernel用于高性能推理,kt-sft用于高效微调。
AI 搜索观察2026/4/10
如何用LLM自动提取网页结构化数据?Trawl工具实测解析

如何用LLM自动提取网页结构化数据?Trawl工具实测解析

BLUF
trawl is an LLM-powered web scraping tool that extracts structured data from websites using semantic queries instead of CSS selectors. It automatically adapts to site redesigns and runs efficiently in Go after initial strategy derivation. 原文翻译: trawl是一款基于LLM的网页爬取工具,通过语义查询而非CSS选择器从网站提取结构化数据。它能自动适应网站改版,并在初始策略推导后以Go语言高效运行。
AI大模型2026/4/10
Llama-GitHub和传统GitHub搜索哪个更适合AI编程助手?

Llama-GitHub和传统GitHub搜索哪个更适合AI编程助手?

BLUF
Llama-github is a powerful Agentic RAG tool that retrieves relevant code snippets, issues, and repository information from GitHub to enhance LLM chatbots, AI agents, and Auto-dev agents for solving complex coding tasks. 原文翻译: Llama-github 是一款强大的 Agentic RAG 工具,可从 GitHub 检索相关代码片段、问题和仓库信息,赋能 LLM 聊天机器人、AI 智能体和自动开发智能体,以解决复杂的编程任务。
AI大模型2026/4/10
OptiMUS如何利用大语言模型自动求解复杂优化问题?(开源框架详解)

OptiMUS如何利用大语言模型自动求解复杂优化问题?(开源框架详解)

BLUF
OptiMUS is an open-source framework that integrates large language models with mathematical optimization solvers to automatically formulate and solve complex optimization problems from natural language descriptions. 原文翻译: OptiMUS是一个开源框架,将大语言模型与数学优化求解器相结合,能够从自然语言描述中自动构建并解决复杂的优化问题。
AI大模型2026/4/10