Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
-
Updated
Aug 23, 2026 - C++
8000
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
A lightweight C++ RDMA library for InfiniBand networks.
Switch ML Application
A graph-based distributed in-memory store that leverages efficient graph exploration to provide highly concurrent and low-latency queries over big linked data
This is the source code for our (Tobias Ziegler, Carsten Binnig and Viktor Leis) published paper at SIGMOD’22: ScaleStore: A Fast and Cost-Efficient Storage Engine using DRAM, NVMe, and RDMA.
Sherman: A Write-Optimized Distributed B+Tree Index on Disaggregated Memory
Composable and Embeddable Communication Runtime for Distributed AI Services
A lightweight parameter server interface
Multi-core Window-Based Stream Processing Engine
This is the implementation repository of our OSDI'23 paper: SMART: A High-Performance Adaptive Radix Tree for Disaggregated Memory.
This is the implementation repository of our FAST'23 paper: FUSEE: A Fully Memory-Disaggregated Key-Value Store.
rFaaS: a high-performance FaaS platform with RDMA acceleration for low-latency invocations.
High performance RDMA-based distributed feature collection component for training GNN model on EXTREMELY large graph
Passive Disaggregated Persistent Memory at USENIX ATC 2020.
DingoFS is a distributed file system built for AI workloads.
A high-performance RDMA distributed file system for fast LLM Inference and GPU Training.
Add a description, image, and links to the rdma topic page so that developers can more easily learn about it.
To associate your repository with the rdma topic, visit your repo's landing page and select "manage topics."