#Rdma

kvcache-ai

Mooncake

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

redis

rueidis

A fast Golang Redis client that supports Client Side Caching, Auto Pipelining, RDMA, etc.

openlake-project

openlake

OpenLake is a high performance storage engine for efficient LLM inference and GPU Training

uccl-project

uccl

UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)

spidernet-io

spiderpool

Underlay and RDMA network solution of the Kubernetes, for bare metal, VM and any public cloud

valkey-io

valkey-go

A fast Golang Valkey client that supports Client Side Caching, Auto Pipelining, and RMDA.