A GPU communication library for expert-parallel MoE dispatch and combine, with FP8 dispatch and NVLink/RDMA support for training and inference.
10.3K1.5KCudaMITUpdated 4 days ago
Language
Open-source projects written in Cuda, ranked by stars with AI summaries and license info.
A GPU communication library for expert-parallel MoE dispatch and combine, with FP8 dispatch and NVLink/RDMA support for training and inference.
An open-source book and code collection of modern CUDA learning notes, with 200+ kernels covering HGEMM, FP8/FP4 GEMM, and Flash-Attention.