This is the first release of FMS Model Optimizer. It provides the core functionality:
- **Python API to enable model quantization:** With the addition of a few lines of codes, module-level and/or function-level operations replacement will be performed.
- **Robust:** Verified for INT 8/4-bit quantization on important vision/speech/NLP/object detection/LLMs.
- **Flexible:** Options to analyze the network using PyTorch Dynamo, apply best practices, such as clip_val initialization, layer-level precision setting, optimizer param group setting, etc. during quantization.
- **State-of-the-art INT and FP quantization techniques** for weights and activations, such as SmoothQuant, SAWB+ and PACT+.
- **Supports key compute-intensive operations** like Conv2d, Linear, LSTM, MM and BMM
What's Changed
* Initial setup by tharapalanivel in https://github.com/foundation-model-stack/fms-model-optimizer/pull/1
* Initial commit for optimization techniques by tharapalanivel in https://github.com/foundation-model-stack/fms-model-optimizer/pull/9
* Add dynamic build versioning by hickeyma in https://github.com/foundation-model-stack/fms-model-optimizer/pull/12
* [ci]: Restructure GitHub workflows by hickeyma in https://github.com/foundation-model-stack/fms-model-optimizer/pull/13
* Clear notebook output by tharapalanivel in https://github.com/foundation-model-stack/fms-model-optimizer/pull/15
* Improve README readability by tharapalanivel in https://github.com/foundation-model-stack/fms-model-optimizer/pull/19
* Change project name to correspond to pypi package name by hickeyma in https://github.com/foundation-model-stack/fms-model-optimizer/pull/18
* Set smoothq_alpha as buffer by andrea-fasoli in https://github.com/foundation-model-stack/fms-model-optimizer/pull/20
* Fix device for smoothquant activation scales by andrea-fasoli in https://github.com/foundation-model-stack/fms-model-optimizer/pull/21
* test: Add checks for unit tests that require Nvidia GPU by hickeyma in https://github.com/foundation-model-stack/fms-model-optimizer/pull/14
* tox: Add base Python version to tox environment by hickeyma in https://github.com/foundation-model-stack/fms-model-optimizer/pull/24
* Fix symmetric behavior (issue 22) by andrea-fasoli in https://github.com/foundation-model-stack/fms-model-optimizer/pull/26
* ci: Add Ruff for lint and code formatting by hickeyma in https://github.com/foundation-model-stack/fms-model-optimizer/pull/30
* Update pre-commit requirement from <4.0,>=3.0.4 to >=3.0.4,<5.0 by dependabot in https://github.com/foundation-model-stack/fms-model-optimizer/pull/16
* doc: Update dev env section of the contributing guide by hickeyma in https://github.com/foundation-model-stack/fms-model-optimizer/pull/29
New Contributors
* tharapalanivel made their first contribution in https://github.com/foundation-model-stack/fms-model-optimizer/pull/1
* hickeyma made their first contribution in https://github.com/foundation-model-stack/fms-model-optimizer/pull/12
* andrea-fasoli made their first contribution in https://github.com/foundation-model-stack/fms-model-optimizer/pull/20
* dependabot made their first contribution in https://github.com/foundation-model-stack/fms-model-optimizer/pull/16
**Full Changelog**: https://github.com/foundation-model-stack/fms-model-optimizer/commits/v0.2.0