#post-training-quantization Repositories
Discover 12 active open source GitHub repositories tagged with #post-training-quantization, accumulating 21,589 total stars (averaging 1,799 stars per project). Leading this topic is NVIDIA/Model-Optimizer with 5,646 stars.
12 repositories total
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
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.
micronet, a model compression and deploy lib. compression: 1ใquantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)ใLow-Bit(โค2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2ใ pruning: normalใregular and group convolutional channel pruning; 3ใ group convolution structure; 4ใbatch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/in
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.
Model Compression Toolbox for Large Language Models and Diffusion Models
Frequently Asked Questions
What is the most popular #post-training-quantization repository on GitHub?
The top ranked open source #post-training-quantization project on GitHub is NVIDIA/Model-Optimizer with 5,646 stars. A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
Which programming languages are most used in #post-training-quantization repositories?
Among the top ranked #post-training-quantization projects on GitHub, the most common programming languages are Python.
How is the #post-training-quantization repository ranking calculated?
We track 12 active open source repositories tagged with #post-training-quantization (500+ stars), totaling 21,589 stars with an average of 1,799 stars per repository. Rankings update daily from the GitHub API.