#sparsity Repositories
Discover 7 active open source GitHub repositories tagged with #sparsity, accumulating 16,506 total stars (averaging 2,358 stars per project). Leading this topic is NVIDIA/Model-Optimizer with 5,646 stars.
7 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
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.
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
Frequently Asked Questions
What is the most popular #sparsity repository on GitHub?
The top ranked open source #sparsity 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 #sparsity repositories?
Among the top ranked #sparsity projects on GitHub, the most common programming languages are Python.
How is the #sparsity repository ranking calculated?
We track 7 active open source repositories tagged with #sparsity (500+ stars), totaling 16,506 stars with an average of 2,358 stars per repository. Rankings update daily from the GitHub API.