Top Repositories on Github with TechGarden

MoBA: Mixture of Block Attention for Long-Context LLMs

This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"

一个基于 AI 的 Hacker News 中文播客项目，每天自动抓取 Hacker News 热门文章，通过 AI 生成中文总结并转换为播客内容。

Official Repo for Open-Reasoner-Zero

An AI chat bot for small and medium-sized teams, supporting models such as Deepseek, Open AI, Claude, and Gemini. 专为中小团队设计的 AI 聊天应用，支持 Deepseek、Open AI、Claude、Gemini 等模型。

Streaming highlighting with Shiki. Useful for highlighting text streams like LLM outputs.

Token Sniper Bot in Raydium written by Rust

Implementation of the sparse attention pattern proposed by the Deepseek team in their "Native Sparse Attention" paper