GRASS: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients
Aashiq Muhamed, Oscar Li, David Woodruff, Mona T. Diab, Virginia Smith
- Anthology ID:
- 2024.emnlp-main.835
- Volume:
- Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 14978–15003
- Language:
- URL:
- https://preview.aclanthology.org/landing_page/2024.emnlp-main.835/
- DOI:
- 10.18653/v1/2024.emnlp-main.835
- Cite (ACL):
- Aashiq Muhamed, Oscar Li, David Woodruff, Mona T. Diab, and Virginia Smith. 2024. GRASS: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 14978–15003, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- GRASS: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients (Muhamed et al., EMNLP 2024)
- PDF:
- https://preview.aclanthology.org/landing_page/2024.emnlp-main.835.pdf