-
Institute of Computing Technology, Chinese Academy of Science
- Beijing
- liaoyunkun.github.io
Starred repositories
🥢像老乡鸡🐔那样做饭。主要部分于2024年完工,非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》,并做归纳、编辑与整理。CookLikeHOC.
NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process communication and coordination overheads by allowing programmer…
🧮 A collection of resources to learn mathematics for machine learning
A library of common data structures and algorithms written in C.
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention
Ongoing research training transformer models at scale
Learn Cpp from Beginner to Advanced ✅ Practice 🎯 Code 💻 Repeat 🔁 One step solution for c++ beginners and cp enthusiasts.
A Primer on Memory Consistency and Cache Coherence (Second Edition) 翻译计划
Optimized primitives for collective multi-GPU communication
Analyze computation-communication overlap in V3/R1.
TX only RoCEv2. Super stripped down version of a RoCEv2 endpoint.
This is the official code implementation of A Survey on Unlearnable Data.
AIInfra(AI 基础设施)指AI系统从底层芯片等硬件,到上层软件栈支持AI大模型训练和推理。
A high-performance and easy-to-use RDMA library, called SnowRDMA.