Cuda Kernel Optimizer

Use when optimizing or diagnosing GPU workload performance with CUDA, CUTLASS, Triton, PyTorch, vLLM or TensorRT-LLM; interpreting NCU, Nsys or PyTorch Profiler evidence; or preparing the workload and correctness checks for such optimization. General coding, skill maintenance and conceptual GPU questions do not require the optimization workflow.

troycheng 216d811 40 files · 906.0 KB Updated

File contents

troycheng/cuda-kernel-optimizer/tree/main/skills/cuda-kernel-optimizer commit 216d81119a

Frequently asked questions

npx skillmds@latest add troycheng/cuda-kernel-optimizer