Shypd.aiThe largest open index of AI toolsKernelBench is an open-source benchmark and toolkit for evaluating LLMs' ability to generate efficient GPU kernels. It supports Torch to CUDA conversion and other domain-specific languages, helping assess and improve LLMs in high-performance code generation.
Trending
About
KernelBench is an open-source benchmark and toolkit designed to evaluate the capability of large language models (LLMs) in generating efficient GPU kernels. It specifically tasks LLMs with transpiling PyTorch operators into optimized CUDA or other DSL kernels for target GPUs. The platform offers four levels of problem categories, ranging from single-kernel operators to full model architectures, allowing for comprehensive evaluation. KernelBench provides core functionality for checking correctness and measuring performance against reference PyTorch operators, using a metric called `fast_p` to quantify tasks that are both correct and achieve a specified speedup. It supports various GPU programming languages and DSLs, including CUDA, Triton, and HIP for AMD GPUs, and offers flexible setup options for local or cloud-based evaluation.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
