Highlights
- Pro
Lists (15)
Sort Name ascending (A-Z)
Starred repositories
Implement a Pytorch-like DL library in C++ from scratch, step by step
hpc 教程,包含集合通信(mpi、nccl)、cuda 编程、向量化 SIMD、RDMA 通信等
🔥 大模型 & Agent 面试八股文完全指南 | LLM & Agent Interview Preparation Guide
Building General-Purpose Robots Based on Embodied Foundation Model
FlashInfer: Kernel Library for LLM Serving
FlashKDA: high-performance Kimi Delta Attention kernels
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
An SDK (Software Development Kit) for building commercial-grade, AI-native, 3GPP, and O-RAN compliant 5G/6G gNB software on NVIDIA-accelerated computing platforms.
A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
astrbot‘s plugin: group_digest
PTX ISA 9.1 documentation converted to searchable markdown. Includes Claude Code skill for CUDA development.
Professional Antigravity Account Manager & Switcher. One-click seamless account switching for Antigravity Tools. Built with Tauri v2 + React (Rust).专业的 Antigravity 账号管理与切换工具。为 Antigravity 提供一键无缝账号切…
Draft-Target Disaggregation LLM Serving System via Parallel Speculative Decoding.
MusicSquare: A simple music search, download, and play website. (简易音乐搜索,下载和播放网页,支持咪咕,网易云,QQ和酷我音乐)
Fast and memory-efficient exact kmeans
Persistent Kernel + JIT-Injected Operators (CUDA)
AstrBot 自主学习插件 — 让 AI 聊天机器人自主学习对话风格、理解群组黑话、管理社交关系与好感度、自适应人格演化,像真人一样自然对话。
A lightweight inference engine supporting speculative speculative decoding (SSD).
Tutel MoE: Optimized Mixture-of-Experts Library, Support GptOss/DeepSeek/Kimi-K2/Qwen3 using FP8/NVFP4/MXFP4
Smallest transformer that can add two 10-digit numbers
Source files to replicate experiments in my RLC 2025 paper.