About
SparseML enables network sparsity with a few lines of code, through open-source libraries, to boost neural network inference performance.
SparseML allows you to create inference-optimized sparse models using state-of-the-art pruning and quantization algorithms. Models trained with SparseML can then be exported to ONNX and deployed with DeepSparse for GPU-class performance on CPU hardware.
Media
Similar products
Neural Magic products
-
DeepSparse
DeepSparse
Deep Learning Software
-
SparseZoo
SparseZoo
Deep Learning Software