grouped-gemm

Here are 4 public repositories matching this topic...

NVIDIA / cudnn-frontend

cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.

Updated Aug 15, 2026
Python

shuochen0113 / ufg-ggemm

Star

High-performance grouped matrix multiplication for fine-grained and ultra-fine-grained MoE workloads.

deep-learning cuda pytorch cutlass gpu-kernels mixture-of-experts grouped-gemm

Updated Jul 30, 2026
Cuda

shiloz-stack / blackwell-moe-kernel-scheduler

Star

Workload-aware persistent expert-tile scheduling for irregular MoE inference kernels on NVIDIA Blackwell GPUs

cuda load-balancing mixture-of-experts kernel-scheduling nvidia-blackwell grouped-gemm moe-inference

Updated Aug 13, 2026
Cuda

ChaoyuWang04 / Switchboard_MoE-DeepEP

Star

Hand-built MoE expert parallelism: routing-skew capture, fused grouped-GEMM Triton kernels, 2-all2all dispatch/combine, overlap ablations — proving by counter-example why DeepEP exists.

cuda triton moe nccl mixture-of-experts all-to-all deepseek gpu-profiling distributed-inference kernel-optimization deepep grouped-gemm expert-parallelism

Updated Jul 18, 2026
Python

Improve this page

Add a description, image, and links to the grouped-gemm topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the grouped-gemm topic, visit your repo's landing page and select "manage topics."

Learn more