I build practical AI systems, with a focus on traceability, reliability, and useful outcomes.
Contact: wenqiaokang@outlook.com
nano-lmcache
A step-by-step implementation of KV cache reuse, with runnable examples for prefix matching and cache storage.
Python · LLM inference · Examples
Updated daily from GitHub activity.
📚 An educational, step-by-step implementation of LLM KV cache reuse — learn prefix caching, chunk keys, storage & eviction, from pure Python to GPU tensors and vLLM integration. Inspired by LMCache.
Forked from binary-husky/gpt_academic
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
Python
Forked from zhinianboke/xianyu-auto-reply
闲鱼自动回复管理系统是一个基于 Python + FastAPI 开发的自动化客服系统，专为闲鱼平台设计。系统通过 WebSocket 连接闲鱼服务器，实时接收和处理消息，提供智能化的自动回复服务。同时集成闲鱼自动发货，自动评价，自动擦亮等功能，实现闲鱼虚拟商品自动化流程。
Python
Forked from lingdojo/kana-dojo
Aesthetic, minimalist platform for learning Japanese inspired by Duolingo and Monkeytype, built with Next.js and sponsored by Vercel. Beginner-friendly with plenty of good first issues - all contri…
TypeScript
Forked from ARPAHLS/rooms
A secure, local-first Python framework for orchestrating complex multi-agent think tanks with dynamic expertise-weighted routing.
Python