Shypd.aiThe largest open index of AI toolsHidet is an open-source deep learning compiler written in Python that optimizes DNN models from PyTorch and ONNX into efficient CUDA kernels. It focuses on inference workloads on NVIDIA GPUs.
Trending
About
Hidet is an open-source deep learning compiler, primarily written in Python, designed to enhance the efficiency of deep neural network (DNN) models. It facilitates the end-to-end compilation of models from popular frameworks like PyTorch and ONNX into highly optimized CUDA kernels. The framework applies a series of graph-level and operator-level optimizations to significantly improve performance, particularly for inference workloads on NVIDIA GPUs. Hidet requires a Linux operating system, CUDA Toolkit 11.6+, and Python 3.9+ for operation. It can be easily installed via pip or built from source, offering flexibility for developers. The project is actively developed by a team at CentML Inc. and is released under the Apache 2.0 license.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
