XNNPACK
XNNPACK copied to clipboard
google
High-efficiency floating-point neural network inference operators for mobile, server, and Web
Split up aarch32 instruction encoding tests to avoid stack frame size errors in certain build configs
![copybara-service[bot] avatar](https://avatars.githubusercontent.com/in/44061?v=4 "copybara-service[bot] avatar"){kind=avatar}
SSE transpose x16 microkernel (8x8) - New microkernel - Unit tests - Benchmarks
aarch32 transpose TBL microkernel - New microkernel - Unit tests - Benchmarks
aarch43 transpose ZIP microkernel - New microkernel - Unit tests - Benchmarks
Fix incompatible std cxx opts when targeting windows
Quantization support for TRANSPOSE_CONV in XNNPACK delegate
Support missing bias for TRANSPOSE_CONV in the XNNPACK delegate