Version 1.0.3

- Fixed bug where version could not be detected, when imported as a
    submodule
- Now possibility to package as .deb package
- Added new checks and tests

Version 1.0.2

- Full support for armv7l plattform on linux
- Bela examples now in separate repository
- Benchmarks part of test suite when making pull request
- Fixed windows test suite
- Multiple improvements in CMake build chain

Version 1.0.1

Fixes #11. Issue where the concurrentqueue lib would not be found in the prebuilt binaries or installed lib.

Version 1.0.0

Major update of the libary that includes API changes (have a look at the anira usage guide or the examples for more information). Multiple new features have been added:
- Multichannel support
- Support for input and output of multiple tensors including threadsafe methods to retrieve and pass their state in the anira::PrePostProcessor
- New anira::Context that uses the same thread pool independent of the anira::InferenceConfig the anira::InferenceHandler has been initialized with
- Clap plugin example
- Enhanced inference job submission

Version 0.1.3

Updated libtorch to 2.4.1. Fixes issue libomp not bundled with libtorch for macOS arm64. x86_64 macOS stays with 2.2.2 since new version binaries are not build by pytorch.

Version 0.1.2

- New timestamps via counting inference buffers
- Enhanced thread synchronization and data sharing between threads
- Windows Ninja generator support
- Enhanced Windows dynamic libs
- New default values in InferenceConfig
- Default threadsafe structs switched to atomic
- Solved debug build issues with windows
- Port to new organization
- Updated documentation

Version 0.1.1

New Bela support and examples and new thread synchronisation option with
raw atomics

Version 0.1.0 - new anira:InferenceConfig layout

Version 0.0.8 - improved latency calculation

Version 0.0.7