neuralmagic/deepsparse v0.5.0

DeepSparse v0.5.0

on GitHub

New Features:

• None

Changes:

• Performance optimizations implemented for binary elementwise operations, where both inputs come from the same source buffer. One of the inputs may have intermediate unary operations.
• Performance optimizations implemented for binary elementwise operations where one of the inputs is a constant scalar.
• Small performance improvement for large batch sizes (> 64) on quantized ResNet.

Resolved Issues:

• Assertion deepsparse num_sockets removed when too many sockets were requested, causing users to experience a crash.
• Rare assertion failure fixed when a nonlinearity appeared between an elementwise addition and a convolution or gemm.
• Broken URLs for classification and detection examples updated in the contained READMEs.

Known Issues:

• None