Popular GitHub Repositories for Learnable Sparsity

Sparsity-aware deep learning inference runtime for CPUs

PyTorch native quantization and sparsity for training and inference

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

PaddleSlim is an open-source library for deep model compression and architecture search.

A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA

This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation of the convolution to learnable non linear activations in each pixel.

More readable and flexible yolov5 with more backbone(gcn, resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer, etc) and (cbam，dcn and so on), and tensorrt

[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

[ICML2025] Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity

An innovative library for efficient LLM inference via low-bit quantization

Reference ImageNet implementation of SelecSLS CNN architecture proposed in the SIGGRAPH 2020 paper "XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera". The repository also includes code for pruning the model based on implicit sparsity emerging from adaptive gradient descent methods, as detailed in the CVPR 2019 paper "On implicit filter level sparsity in Convolutional Neural Networks".

AutoNode: A Neuro-Graphic Self-Learnable Engine for Cognitive GUI Automation

[ICLR 2023] "More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity"; [ICML 2023] "Are Large Kernels Better Teachers than Transformers for ConvNets?"

Source code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional Representations), ICLR 2022

Always sparse. Never dense. But never say never. A Sparse Training repository for the Adaptive Sparse Connectivity concept and its algorithmic instantiation, i.e. Sparse Evolutionary Training, to boost Deep Learning scalability on various aspects (e.g. memory and computational time efficiency, representation and generalization power).

Sparse and structured neural attention mechanisms

[CVPR 2024] Official code for "Text-Driven Image Editing via Learnable Regions"

Neural Code Comprehension: A Learnable Representation of Code Semantics