bwnjnOEI
Follow
Lists (7)
Stars
📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).
Make websites accessible for AI agents
PaSa -- an advanced paper search agent powered by large language models. It can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant refe…
800,000 step-level correctness labels on LLM solutions to MATH problems
Clean, minimal, accessible reproduction of DeepSeek R1-Zero
Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
A command line tool for porting Excalidraw diagrams to Gliffy and draw.io.
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
Magic to turn Cursor/Windsurf as 90% of Devin
📄 A curated list of awesome .cursorrules files
🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library
🍏 + 🎯 + 🐍 = Everything you need to query Apple's FindMy network!
⛅️ 精选的 Cloudflare 工具、开源项目、指南、博客和其他资源列表。/ ⛅️ A curated list of Cloudflare tools, open source projects, guides, blogs and other resources.
Python APIs for web automation, testing, and bypassing bot-detection.
Xiaomi Home Integration for Home Assistant
A lightweight task engine for building stateful AI agents that prioritizes simplicity and flexibility.
Recipes to scale inference-time compute of open models
Build event-driven workflows with python async functions
🕵️♂️ Collect a dossier on a person by username from thousands of sites
Code and data for the paper "Why think step by step? Reasoning emerges from the locality of experience"
LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.
Run your own AI cluster at home with everyday devices 📱💻 🖥️⌚
SafeLine is a self-hosted WAF(Web Application Firewall) / reverse proxy to protect your web apps from attacks and exploits.
🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…