* optimise i8*u8, u8*i8 and u8*u8 matrix products (and convo)
0.15.2
* bump prost dep
0.15.1
* some optimisations for arm32 (cortex-a7 and a9)
0.15.0
* Switched the order of item_type and item_type_vendor in the NNEF tendor format to be consistent with NNEF-tools, and changed the item_type of integers due to an error in the specification. Breaking for tensor files containing integers or strings. * Scan output batching optimisation * Concat pulsification over a secondary axis * new aarch64 16x4 f32 kernel
0.14.2
* better handling of errors in ONNX parser * fix/workaround some performance regressions bubling from recent ndarray changes
0.14.1
* ONNX ConvTranspose, Gather, GatherND, GatherElements, Scatter, ScatterND, ScatterElements support (and NNEF deconv) * Fixes around integer serialisation in NNEF * workaround subtle breaking changes in ndarray (between 0.15.1 and 0.15.2)