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

v1.3.7

• Add more docstrings and comments
• Minor bug fixing

Full Changelog: v1.3.6...v1.3.7

v1.3.6

What's Changed

• fix bug:inversed_idx do not match the origin index by @pleb631 in #321
• Remove ch_groups in tp.importance

New Contributors

• @pleb631 made their first contribution in #321

Full Changelog: v1.3.5...v1.3.6

v1.3.5: bugfixing

What's Changed

• Merge by @VainF in #312
• V1.3 by @VainF in #315

Full Changelog: v1.3.4...v1.3.5

v1.3.4

What's Changed

• fix nan and inf bug in sparse learning by @HollyLee2000 in #310
• Fixed a bug in interactive pruning + iterative pruning + sparse training by @VainF in #311

New Contributors

• @HollyLee2000 made their first contribution in #310

Full Changelog: v1.3.3...v1.3.4

v1.3.3: Bugfixing

Full Changelog: v1.3.2...v1.3.3

v1.3.2: A regular release with minor BugFixing.

• Fixed an issue in grouped conv.
• Include more normalization layers in importance estimation
• Add a MACs / FLOPs counter for timm Swin
• Add sentinel normalizer, which normalizes the importance score by utilizing the k-th smallest element.
• ...

v1.3.1

• Fixed several problems

v1.3.0

What's Changed

• Add head pruning for transformers.
• Add benchmark tools for latency, memory, throughput, etc.
• Improved interfaces.
• Transformer Pruning Benchmarks: https://github.com/VainF/Torch-Pruning/tree/master/examples/transformers
• ...

Full Changelog: v1.2.5...v1.3.0

v1.2.5

What's Changed

• Pruning & Finetuning examples for Vision Transformers
• ADD Group Hessian / Taylor Importance. Quantitative results can be found here.
• ADD new OpCounters for timm attention.
• Fixed some bugs in ViT examples and iterative pruning
• ...

Full Changelog: v1.2.4...v1.2.5