Layer-wise heterogeneity-guided heterogeneous pruning: An LLM compression method
Abstract Large language models (LLMs) have become foundational in modern natural language processing, enabling diverse applications such as conversational AI, code generation, and scientific discovery. Their massive parameter counts impose significant computational and memory demands, hindering depl...
Tallennettuna:
| Päätekijät: | , , , , , , , |
|---|---|
| Aineistotyyppi: | Artigo |
| Kieli: | Inglês |
| Julkaistu: |
Springer
2026-04-01
|
| Sarja: | Journal of King Saud University: Computer and Information Sciences |
| Aiheet: | |
| Linkit: | https://doi.org/10.1007/s44443-026-00724-4 |
| Tagit: |
Ei tageja, Lisää ensimmäinen tagi!
|