1 repo
Awesome GitHub RepositoriesModel Pruning Techniques
Methods for reducing the size and complexity of neural networks by removing or consolidating layers.
Distinguishing note: Focuses on structural reduction of the network architecture to decrease latency, distinct from precision-based compression.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Model Pruning Techniques. Refine with filters or upvote what's useful.
Awesome Model Pruning Techniques GitHub Repositories
Find the best repos with AI.We'll search the best matching repositories with AI.
- deepspeedai/DeepSpeed
deepspeedai/DeepSpeed
41,638View on GitHubDeepSpeed is a high-performance library designed to scale deep learning model training and inference across massive clusters of GPUs and compute nodes. It provides a comprehensive suite of tools for distributed training, enabling the execution of models that exceed the memory capacity of single devices through advanced parameter partitioning, pipeline-based model parallelism, and memory-efficient state offloading. The framework distinguishes itself through specialized communication-efficient optimizers and hardware-aware acceleration techniques. By utilizing gradient compression, quantization
The framework decreases inference latency by reducing the number of hidden layers in a neural network while maintaining consistent layer width.
Pythonbillion-parameterscompressiondata-parallelism
