Release v0.8.1

This release includes:

* AutoML improvements:

    * possibility to configure search space from YAML scenario
    * possibility to switch between simulation and actual hardware for evaluation
    * possibility to define target metric
* Improved reporting infrastructure
* Introduced support for AI8X runtime
* Improved Protocol infrastructure

    * added passing messages directly to required buffers in Kenning Zephyr Runtime
    * added possibility to pass logs from device running Kenning Zephyr Runtime
* Added possibility to configure reports from scenario level
* Improved integration with ROS 2

    * Added possibility to run Kenning as ROS 2 node
* Runtimes improvements:

    * Updated IREE support to 3.6.0 version (Kenning and Kenning Zephyr Runtime)
    * Introduced initial ExecuTorch support (Kenning and Kenning Zephyr Runtime)
    * Introduced initial tinygrad support
* Introduced numerous improvements with regard to compatibility between blocks

For installation instructions, see the [README](https://github.com/an…

…tmicro/kenning#module-installation-with-pip) or [Gallery of use cases](https://antmicro.github.io/kenning/kenning-gallery.html)

Changes:

* Introduced improvements when passing IO and model data between Optimizer and Runtime blocks
* Improved and sped up parsing of Renode profiler results
* Introduced SparseGPT, GPTQ and SparseGPT+GPTQ optimizers for LLMs
* Added ModelWrappers for Phi-2 and Mistral 7B models
* Added example of summarization dataset
* Introduced support for LLEXT module building for Kenning Zephyr Runtime
* Introduced anomaly detection dataset handler for CSV files (on example of CATS dataset)
* Introduced VAE model
* Introduced Platform class for holding data necessary for Optimizers and HW-aware optimizations
* Introduced AutoML class for running automatic model architecture search
* Introduced AutoPyTorch-based AutoML implementation
* Introduced gallery examples:
  * [Anomaly detection model deployment on MCU](https://antmicro.github.io/kenning/gallery/anomaly-detection-on-mcu.html)
  * [AutoML-based search for anomaly detection models](https://antmicro.github.io/kenning/gallery/anomaly-detection-automl.html)
* Added support for YAML-based scenarios
* Minor fixes in drawing and reporting modules

Release v0.0.3

* Introduced improvements when passing IO and model data between Optimizer and Runtime blocks
* Improved Renode profiler parsing
* Introduced SparseGPT, GPTQ and SparseGPT+GPTQ optimizers for LLMs
* Added ModelWrappers for Phi-2 and Mistral 7B models
* Added example summarization dataset
* Introduced support for LLEXT module building for Kenning Zephyr Runtime
* Introduced anomaly detection dataset handler for CSV files (on example of CATS dataset)
* Introduced VAE model
* Introduced Platform class for holding data necessary for Optimizers and HW-aware optimizations
* Introduced AutoML class for running automatic model architecture search
* Introduced AutoPyTorch-based AutoML implementation
* Added support for YAML-based scenarios
* Added numerous other improvements

Initial Kenning release