Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Making models smaller and faster: quantization, distillation, pruning, sparsity and kernel-level work.
Signals: quantization, model-compression, pruning, knowledge-distillation, gptq, awq, bitsandbytes, sparsity
185 results
A collection of memory efficient attention operators implemented in the Triton language.
A vLLM patch + hand‑written SM120 SASS kernels: 2‑bit MoE experts + an FP4 "delta" cache that recovers precision — matching the official (NV)FP4 checkpoint's quality on consumer Blackwell cards
A curated collection of papers, benchmarks, surveys, and tools for model quantization, covering low-bit networks, LLMs, multimodal and generative models, vector and lattice quantization, and efficient deployment.
Lossy PNG compressor — pngquant command based on libimagequant library
Open Neural Network Exchange to C compiler.
PyTorch native quantization for training and inference
A Lightweight LLM Post-Training Library
Dataflow compiler for QNN inference on FPGAs
Infrastructure for Machine Learning Guided Optimization (MLGO) in LLVM.
NeuralFoil is a practical airfoil aerodynamics analysis tool using physics-informed machine learning, exposed to end-users in pure Python/NumPy.
A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
Design hardware-friendly model architectures and migrate existing LLMs with minimal performance loss
AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.
Awesome LLM compression research papers and tools.
A pytorch quantization backend for optimum
Ollama model direct link generator and installer.
FasterAI: Prune and Distill your models with FastAI and PyTorch
A powerful model compression framework for LLMs and LVLMs, adapted for NVIDIA GPUs and Huawei Ascend NPUs.
Neural Networks with low bit weights on low end 32 bit microcontrollers such as the CH32V003 RISC-V Microcontroller and others
PyTorch implementation of 'Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding' by Song Han, Huizi Mao, William J. Dally
(ECCV'2020 Oral)EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning
PyTorch library to facilitate development and standardized evaluation of neural network pruning methods.
Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning. In ICCV 2019.
24,543 repositories in the index in total.
