Show HN: Agentic CUDA Kernel Optimizer

Automated excerpt

Load or generate a signature, input cases, reference kernel, and initial kernel. Float32 GEMM on an RTX 3060 Laptop GPU, with NVIDIA research and Nsight Compute enabled. Generated CUDA kernels also run on the local GPU.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.