What's Changed
- Add benchmark CLI: trtutils benchmark command by @justincdavis in #26
- Improved Docs by @justincdavis in #27
- Kernel abstraction by @justincdavis in #28
- Faster V10+EfficientNMS Decode by @justincdavis in #29
- CUDA Resizing Kernels by @justincdavis in #30
Full Changelog: v0.3.5...v0.4.0