v1.6.1: enhance code style

Enhance code style:

• Standardize import organization across all Python files following PEP 8
• Add comprehensive Google-style docstrings to all public functions and classes
• Enhance type hints throughout the codebase for better IDE support
• Improve error handling with descriptive messages and proper exception types
• Enhance setup.py with better metadata and comprehensive classifiers
• Improve utility functions with proper documentation and decorators
• Add proper code formatting and style consistency
• Update version to 1.6.1

v1.6.0: Refactor the core Dependency module

What's Changed

• V1.6.0: Refactor the core dependency module by @VainF in #501

Full Changelog: v1.5.3...v1.6.0

v1.5.3

What's Changed

• BatchnormPruner: Skip running mean/var when tracking_running_stats=False by @TingyiChen in #466
• V2.0 by @VainF in #493
• V2.0 by @VainF in #494

New Contributors

• @TingyiChen made their first contribution in #466

Full Changelog: v1.5.2...v1.5.3

v1.5.2

What's Changed

• Add examples for Qwen-2.5, DeepSeek-R1-Distill
• Improved interfaces and tools.
• Merge by @VainF in #465
• V2.0 by @VainF in #472

Full Changelog: v1.5.1...v1.5.2

v1.5.1

What's Changed

• Fix bug: moved handling of the case where imp is none before len is c… by @JamesKing76 in #440
• Fixed some issues in Qwen-2 Pruning. Add examples for Qwen-2.5.

New Contributors

• @JamesKing76 made their first contribution in #440

Full Changelog: v1.5.0...v1.5.1

v1.5.0: Add SliceOp; Support Phi-3 & Qwen-2

What's Changed

• Merge by @VainF in #434
• Add SliceOp; Add Phi-3 & Qwen-2 by @VainF in #435

Full Changelog: v1.4.3...v1.5.0

v1.4.3

What's Changed

• Fixed some issues in GQA Pruning
• [fix] Clarify variable naming in linear_scheduler function, add typing by @janumiko in #423

New Contributors

• @janumiko made their first contribution in #423

Full Changelog: v1.4.2...v1.4.3

v1.4.2

What's Changed

• fixed a bug in attention head pruning
• fixed potentially buggy typo by @Alejandro-Casanova in #405

New Contributors

• @Alejandro-Casanova made their first contribution in #405

Full Changelog: v1.4.1...v1.4.2

v1.4.1

What's Changed

• Add Isomorphic Pruning, an improved algorithm for global pruning.
• Unify local/global/isomorphic pruning with Scope for importance ranking
• Allow user-defined scope for importance ranking. The following key-value pair (model.layer1, model.layer2): 0.4 will perform global ranking only within layer1 and layer2, with the pruning ratio of 40%.

  pruner = tp.pruner.MetaPruner(
      ...
      global_pruning=True,
      pruning_ratio=0.5, # default pruning ratio
      pruning_ratio_dict = {(model.layer1, model.layer2): 0.4, model.layer3: 0.2}, 
      # Global pruning will be performed on layer1 and layer2
  )

• Bugfixing

New Contributors

• @Miocio-nora made their first contribution in #380

Full Changelog: v1.4.0...v1.4.1

v1.4.0: Improved Support for Huggingface Transformers & LLMs

What's Changed

• Add support for Grouped Query Attention (GQA) in Huggingface transformers.
• Include minimal examples for Large Language Models (LLaMA-2 & LLaMA-3).

Full Changelog: v1.3.7...v1.4.0