v3.0.7

What's Changed

• Update setup.py to use new email address by @jeremyfowers in #216
• Don't run code at init time! by @jeremyfowers in #220
• Don't require a specific protobuf by @jeremyfowers in #221

Full Changelog: v3.0.6...v3.0.7

v3.0.6

What's Changed

• Move the performance module and Device class under the run module by @jeremyfowers in #215

Full Changelog: v3.0.5...v3.0.6

v3.0.5

What's Changed

• Create examples for the new way of using the api by @jeremyfowers in #211
• Fix process isolation bug by @jeremyfowers in #212
• Allow CI tests to select the directory where their cache and corpus will be placed by @jeremyfowers in #213

Full Changelog: v3.0.4...v3.0.5

v3.0.4

What's Changed

This is a hotfix release.

• Dont throw an error when we can't figure out the parameter count by @jeremyfowers in #210

Full Changelog: v3.0.3...v3.0.4

v3.0.3

What's Changed

Minor changes to make turnkeyml more flexible.

• Support for python 3.11 by @jeremyfowers in #189
• Improve TurnkeyML Framework Extensibility by @jeremyfowers in #209

Full Changelog: v3.0.2...v3.0.3

v3.0.2

What's Changed

Bug Fixes:

• Bug: Monitor on/off should not be part of State by @jeremyfowers in #206
• Fix help menu by @jeremyfowers in #207
• Prevent onnx 1.16.2 from being deployed by @jeremyfowers in #208

Full Changelog: v3.0.1...v3.0.2

v3.0.1

What's Changed

• Fix load_build bug by @jeremyfowers in #204

Full Changelog: v3.0.0...v3.0.1

v3.0.0

Summary

This release is the culmination of a month of work in the refresh branch to re-architect TurnkeyML for the future.

The high-level changes are:

• Stages have been replaced by Tools, which each have their own arguments parser to enable maximum configurability
• Sequences are no longer hardcoded lists of Stages - now users can enter any list of Tools they like
• Everything is a Tool: model discovery, benchmarking, and even cache management functionality (report, list, delete, etc.) are all now modular Tools.
• Plugins now primarily add new Tools. These new Tools can do a lot more than Stages used to be able to, such as:
  • Add a new frontend into the sequence, as a replacement for model discovery. For example, load an LLM checkpoint.
  • Replace the backend of the sequence with something other than our standard benchmarking flow. For example, run an accuracy test.
  • Add utility functions, such as managing the cache or built-in models.
• There is a brand new command line interface and API to expose the new way of doing things.
• The tools documentation has been completely re-written.

Breaking Changes

There are almost too many to list since the whole project has been re-architected. Here are the major things to be aware of:

• Stage classes need to be ported to on to the Tool class.
  • Any reference to stage should be changed to tool, for example the stage_status:: stat is now tool_status::
  • The names of most Tools have been renamed to fit our new naming scheme (see contribution guide).
• There is no longer a notion of benchmark_status, since benchmarking is now a Tool. It's now tool_status::benchmark.
• The build_model() API has been removed. Instead, Tools should be called as their own standalone APIs.
• The benchmark_files() API has been re-named to evaluate_files().
• The repository directory structure has been redone, which changes a lot of imports.
  • For example, turnkeyml.state has State and load_state().
  • See the code organization doc for the full set of changes.

v2.0.3

What's Changed

• Specify how errors should be handled during decoding by @danielholanda in #148

Full Changelog: v2.0.2...v2.0.3

v2.0.2

What's Changed

• Do not set benchmarking error status when a benchmark is skipped by @jeremyfowers in #146
• Relax ORT requirements by @danielholanda in #147

Full Changelog: v2.0.1...v2.0.2