Tensors and Dynamic neural networks in Python with strong GPU acceleration

OneDiff: An out-of-the-box acceleration library for diffusion models.

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Open deep learning compiler stack for cpu, gpu and specialized accelerators

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

An unofficial cuda assembler, for all generations of SASS, hopefully ：）

对 YOLOv3 做模型剪枝，在 oxford hand 数据集上模型的参数量减少 80% ，FLOPs 降低 70%，Infer 的速度可以达到原来的 200%，mAP 基本保持不变

CUDA Templates for Linear Algebra Subroutines

Ristretto: Caffe-based approximation of convolutional neural networks.

Training Low-bits DNNs with Stochastic Quantization