Showing 1-5 of 5 projects
Run frontier AI models locally across devices using RDMA and tensor parallelism
Mooncake is a serving platform for Kimi, a leading LLM service provided by Moonshot AI, focused on disaggregation, inference, and RDMA.
A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology, useful for developers working with GPU-accelerated applications.
Efficient communication library for GPUs, covering collectives, P2P, and EP for AI/ML workloads
A kernel-bypass LibOS architecture for high-performance networking and IO on Linux.
Get weekly updates on trending AI coding tools and projects.