Zing Forum

Topic Guide

LLM Answers & Content Strategy

13607 reads · start with the picks, then keep browsing

LLM推理KV缓存
Trending Topics

Start Here

Read these first to understand what this topic is most worth opening.

Keep Browsing

Use search, sorting, and pagination to keep following the direction you care about.

04
White-box Adversarial Attacks Reveal Social Bias Vulnerabilities in Large Multimodal Models

White-box Adversarial Attacks Reveal Social Bias Vulnerabilities in Large Multimodal Models

This article introduces a white-box adversarial attack study targeting social bias issues in Large Multimodal Models (LMMs). The project provides complete code implementations, including targeted PGD attacks, universal adversarial perturbations, defense evaluation, and noise similarity analysis, serving as an important tool for AI safety research.

对抗攻击多模态模型社会偏见AI安全PGD攻击BLIP-2
Published 2026-07-13 04:11Recent activity 2026-07-13 04:26
05
Hands-On Multi-Modal RAG System: A Local Document Intelligent Q&A Solution Based on Qwen2-VL and CLIP

Hands-On Multi-Modal RAG System: A Local Document Intelligent Q&A Solution Based on Qwen2-VL and CLIP

This article introduces an open-source multi-modal Retrieval-Augmented Generation (RAG) system that combines the Qwen2-VL vision-language model and CLIP encoder. It supports mixed text-image retrieval for PDF documents and provides a complete technical solution for building localized, privacy-controllable intelligent document Q&A systems.

多模态RAG视觉语言模型Qwen2-VLCLIP文档问答PDF处理
Published 2026-07-13 04:09Recent activity 2026-07-13 04:29
06
Building a DNA Large Language Model from Scratch: An Exploration of the Fusion of Bioinformatics and Deep Learning

Building a DNA Large Language Model from Scratch: An Exploration of the Fusion of Bioinformatics and Deep Learning

A complete implementation of a DNA sequence large language model, covering the entire workflow from tokenizer construction, BPE algorithm, embedding layer design, Transformer architecture to prediction and evaluation.

DNA大语言模型生物信息学TransformerBPE分词器
Published 2026-07-13 03:52Recent activity 2026-07-13 03:55
07
Claude Workflow: An Agent Workflow Engine Based on YAML State Machines

Claude Workflow: An Agent Workflow Engine Based on YAML State Machines

This article introduces a plugin designed for Claude Code that uses YAML-defined state machines to drive AI agents in executing complex tasks, supporting state tracking, conditional guards, nested sub-workflows, and a visual dashboard.

AI智能体状态机Claude Code工作流引擎YAML配置智能体编排
Published 2026-07-13 03:22Recent activity 2026-07-13 03:28
08
A Lightweight Validation Framework for Trustworthiness Assessment of Open-Source Large Language Models

A Lightweight Validation Framework for Trustworthiness Assessment of Open-Source Large Language Models

This article introduces a trustworthiness assessment framework for open-source large language models (LLMs), which constructs a lightweight and reproducible evaluation system from three dimensions: security, authenticity, and consistency, supporting local deployment and low-cost validation.

大语言模型可信度评估安全性测试幻觉检测开源LLMOllama
Published 2026-07-13 03:22Recent activity 2026-07-13 03:26
09
n8n Dependency EOL Firewall: A Multi-Agent Automated Dependency Governance Solution

n8n Dependency EOL Firewall: A Multi-Agent Automated Dependency Governance Solution

This article introduces an n8n-based multi-agent workflow system that monitors the health status of code repository dependencies, automatically detects risks such as deprecation, end-of-life (EOL), and version lag, and generates migration PRs automatically.

依赖管理n8n多智能体依赖治理自动化工作流软件供应链
Published 2026-07-13 03:22Recent activity 2026-07-13 03:28
10
LLM Playground: An Interactive Experimental Platform for Large Language Model Behavior

LLM Playground: An Interactive Experimental Platform for Large Language Model Behavior

This article introduces an interactive application for experimenting with and exploring the behavior of large language models (LLMs). It supports features like temperature adjustment, context management, token usage monitoring, and API inference, helping developers gain an in-depth understanding of LLM response characteristics.

大语言模型LLM实验温度参数上下文管理Token监控提示词工程
Published 2026-07-13 03:20Recent activity 2026-07-13 03:30
11
Application of Agentic AI in Football Research: How Multi-Agent Systems Revolutionize Sports Data Analysis

Application of Agentic AI in Football Research: How Multi-Agent Systems Revolutionize Sports Data Analysis

Explore how the agentic-football-ai project combines large language models (LLMs), RAG, vector databases, and multi-agent workflows to bring a new paradigm of intelligent analysis to the field of football research.

Agentic AI足球研究大语言模型RAG向量数据库多智能体系统
Published 2026-07-13 02:52Recent activity 2026-07-13 02:57
12
Tokamak: A Minimalist LLM Inference Engine Built from Scratch

Tokamak: A Minimalist LLM Inference Engine Built from Scratch

Tokamak is a lightweight LLM inference engine implemented from scratch using PyTorch. It fully incorporates core optimization techniques such as KV caching, paged attention, continuous batching, and speculative decoding, and has undergone performance benchmarking against vLLM.

LLM推理PyTorchKV缓存分页注意力投机解码vLLM
Published 2026-07-13 02:21Recent activity 2026-07-13 02:25
13
disp8ch: A Local-First AI Workspace That Turns Conversations into Visual Multi-Agent Workflows

disp8ch: A Local-First AI Workspace That Turns Conversations into Visual Multi-Agent Workflows

disp8ch is a self-hosted AI workspace that upgrades the traditional chat interface into a system for visual workflow orchestration, multi-agent collaboration, and auditable automation. It supports full local operation, requires no API keys, and all data is stored locally.

AI工作空间本地优先多智能体工作流自动化自托管隐私保护
Published 2026-07-13 01:52Recent activity 2026-07-13 01:56
14
Efficient LLM Inference Research Assistant: RAG-based Academic Paper Retrieval and Q&A System

Efficient LLM Inference Research Assistant: RAG-based Academic Paper Retrieval and Q&A System

A retrieval-augmented generation system targeting the field of efficient LLM inference (quantization, KV cache optimization, speculative decoding), built on approximately 30 arXiv papers, capable of generating evidence-based answers based on retrieved paper fragments.

RAGLLM推理检索增强生成arXiv量化KV缓存
Published 2026-07-13 01:51Recent activity 2026-07-13 01:56
15
GreatAegis: Post-Quantum Secure Enterprise AI Gateway Integrating PQC Encryption and AMD ROCm Acceleration

GreatAegis: Post-Quantum Secure Enterprise AI Gateway Integrating PQC Encryption and AMD ROCm Acceleration

An open-source AI gateway for enterprise deployment, integrating post-quantum cryptography (PQC) encryption, dynamic hybrid workload routing, and AMD ROCm-based isolated open-source large model inference, providing dual guarantees for AI security and performance.

后量子密码学PQCAI网关AMD ROCm企业级AI数据安全
Published 2026-07-13 01:22Recent activity 2026-07-13 01:29
16
GitHub Issue Workflow Automation: A Lightweight AI Agent Integration Solution

GitHub Issue Workflow Automation: A Lightweight AI Agent Integration Solution

A lightweight GitHub Issue automation workflow project that helps development teams easily integrate AI agents to automate Issue handling and provides a clear execution tracking mechanism.

GitHub ActionsAI代理Issue自动化工作流DevOps开源项目
Published 2026-07-13 01:22Recent activity 2026-07-13 01:32
17
LLM Memory Visualization Tool: Understand the Memory Mechanisms of Large Model Inference via 3D Interactive Lessons

LLM Memory Visualization Tool: Understand the Memory Mechanisms of Large Model Inference via 3D Interactive Lessons

An open-source interactive 3D visualization project that helps developers understand the memory management mechanisms in LLM inference from first principles, including core concepts like KV caching, pagination, quantization, and shared security.

LLM内存可视化KV缓存量化推理优化3D交互
Published 2026-07-13 01:22Recent activity 2026-07-13 01:28
18
Implementing Qwen 3.5 Inference from Scratch: A Deep Learning Project on CUDA and LLM Principles

Implementing Qwen 3.5 Inference from Scratch: A Deep Learning Project on CUDA and LLM Principles

An educational open-source project that helps developers gain an in-depth understanding of CUDA programming and the working principles of large language models by implementing the inference engine for Qwen 3.5's dense architecture from scratch.

QwenCUDALLM推理从零实现Transformer深度学习
Published 2026-07-13 01:22Recent activity 2026-07-13 01:31
19
LLM Judge AI: A Multi-Model Intelligent Evaluation Platform That Uses AI to Judge AI

LLM Judge AI: A Multi-Model Intelligent Evaluation Platform That Uses AI to Judge AI

An innovative multi-model comparison platform that simultaneously calls multiple large language models via OpenRouter and uses an AI Judge to automatically evaluate response quality, helping users find the most suitable model for specific tasks.

LLM评测模型对比OpenRouterAI Judge多模型模型选择
Published 2026-07-13 01:18Recent activity 2026-07-13 01:30
20
Delegator MCP: Asynchronous Task Orchestration for Multi-Agent Workflows and MCP Server

Delegator MCP: Asynchronous Task Orchestration for Multi-Agent Workflows and MCP Server

Delegator MCP is a TypeScript-based MCP server and asynchronous task orchestrator designed specifically for multi-agent workflows, offering AGY/Codex adapters, an Apple-style dashboard, and production-grade packaging support.

MCP多智能体任务编排TypeScript异步工作流AGY
Published 2026-07-13 00:52Recent activity 2026-07-13 00:56

Next Theme

AI Search Visibility & Indexing

8159 threads