Skip to content

Releases: cda-tum/mqt-predictor

MQT Predictor 2.1.0 Release

11 Oct 08:16
b1c9786
Compare
Choose a tag to compare

👀 What Changed

A year worth of improvements in one release. This is a big one 💥
Amongst others, it adds:

  • Support for Qiskit 1.0
  • Support for numpy 2.0
  • Support for Python 3.13
  • Support for BQSKit
  • Documentation on RtD
  • Several improvements to the overall project structure and packaging, including the adoption of uv for project management

Important

There are currently no pre-trained models for v2.1.0. These will be released in the short future.

🚀 Features and Enhancements

🐛 Bug Fixes

📄 Documentation

🤖 CI

⬆️ Dependencies

70 changes

Full Changelog: v2.0.0...v2.1.0

MQT Predictor 2.0.0 Release

08 Oct 20:39
c403c12
Compare
Choose a tag to compare

What Changed 👀

  • ❇️ Comprehensive rework of the whole Framework:
  • ❇️ New combined approach based on previous ML and RL approaches
  • ❇️ More supported quantum devices and compilation actions
  • 🎨 Support of latest MQT Bench version
  • 🎨 improved imports
  • 🚚 remove deprecated files

📄 Documentation

🤖 CI

⬆️ Dependencies

15 changes

Full Changelog: v1.3.0...v2.0.0

MQT Predictor 1.3.0 Release

15 Jun 11:01
67540e8
Compare
Choose a tag to compare

What Changed 👀

🚀 Features and Enhancements

🐛 Bug Fixes

📄 Documentation

🤖 CI

⬆️ Dependencies

10 changes

Full Changelog: v1.2.2...v1.3.0

v1.2.2 Bugfix: Logging and Numpy Problems

16 Feb 12:32
6ea593e
Compare
Choose a tag to compare

What's Changed

  • Quickfix numpy solving bug in #69
  • Fix two small bugs in #72

Full Changelog: v1.2.1...v1.2.2

v1.2.1 Bugfix: Logging Problem

01 Feb 18:41
4a6cf4b
Compare
Choose a tag to compare

What's Changed

  • Bugfix Logger Statement in #64

Full Changelog: v1.2.0...v1.2.1

v1.2.0 Release: Model Update and Improvements

31 Jan 08:53
5a3404d
Compare
Choose a tag to compare

This release introduces general improvements and updates both the ML and the RL model.

General:

  • Most importantly, the interface to use both models has changed. Please have a look at the readme.

ML Model Update:

  • Provided more training data (3000 instead of 2000 samples).
  • Provided the accordingly trained Random Forest Classifier.
  • More information of the predicted combination of compilation options is returned.
  • The performance evaluation is extended.

RL Model Update:

  • Provided more training data (500 instead of 200 samples).
  • Improved the observation space representation.
  • The trained RL models are not part of the repository itself anymore, but are downloaded when needed at runtime.
  • Two more reward functions are introduced and evaluated.

What's Changed

  • ML Improvements in #59
  • Rl improvements in #61

Full Changelog: v1.1.1...v1.2.0

v1.1.1 Bugfixing

26 Jan 12:48
fe11f36
Compare
Choose a tag to compare

What's Changed

  • 🐛 Bugfix training data handling in #58
  • 🐛 Bugfix Supermarq Feature Calculation in #53
  • 💡 added RL reference to arXiv in #47

Full Changelog: v1.1.0...v1.1.1

v1.1.0 Release: Integration of Reinforcement Learning Model and minor enhancements

11 Dec 18:27
742ab79
Compare
Choose a tag to compare

With this version, MQT Predictor is extended by a reinforcement based learning model.
This model enables the user to compile their quantum circuit based on both the TKET and Qiskit compilers in one compilation flow aiming for better result quality.

Additionally, a few enhancements of the code structure in general are added.

What's Changed

Full Changelog: v1.0.1...v1.1.0

v1.0.1 Release: Bugfixing

14 Oct 13:59
5b33798
Compare
Choose a tag to compare

What's Changed

Full Changelog: v1.0.0...v1.0.1

v1.0.0 Release: Initial Release

13 Oct 12:20
Compare
Choose a tag to compare

This is the initial release for MQT Predictor.