Abstract
Recent work proposed state-space models (SSMs) as an efficient alternative to transformer-based LLMs. Can these models be pruned to further reduce their computation costs? We adapt several pruning methods to the SSM structure, and apply them to four SSM-based LLMs across multiple tasks. We find that such models are quite robust to some pruning methods (e.g. WANDA), while using other methods lead to fast performance degradation.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models (2025)
- You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning (2025)
- Llamba: Scaling Distilled Recurrent Models for Efficient Language Processing (2025)
- A Sliding Layer Merging Method for Efficient Depth-Wise Pruning in LLMs (2025)
- DeltaLLM: Compress LLMs with Low-Rank Deltas between Shared Weights (2025)
- MaskPrune: Mask-based LLM Pruning for Layer-wise Uniform Structures (2025)
- Merging Feed-Forward Sublayers for Compressed Transformers (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 2
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper