Fine-Tuning and Deploying Large Language Models Over Edges: Issues and Approaches

M. Chen, D. Gündüz, K. Huang, W. Saad, M. Bennis, A. V. Feljan, and H. V. Poor, “Distributed learning in wireless networks: Recent progress and future challenges,” IEEE J. Sel. Areas Commun. , vol. 39, no. 12, pp. 3579–3605, Dec. 2021

2021

Earlier work this paper cites.

S. Malladi, T. Gao, E. Nichani, A. Damian, J. D. Lee, D. Chen, and S. Arora, “Fine-tuning language models with just forward passes,” in NeurIPS , vol. 36, New Orleans, LA, USA, Dec. 2023, pp. 53 038–53 075

2023

Earlier work this paper cites.

T. Che, J. Liu, Y. Zhou, J. Ren, J. Zhou, V. Sheng, H. Dai, and D. Dou, “Federated learning of large language models with parameter-efficient prompt tuning and adaptive optimization,” in EMNLP , Singapore, Dec. 2023, pp. 7871–7888

2023

Earlier work this paper cites.

N. Ding, Y. Qin, G. Yang, F. Wei, Z. Yang, Y. Su, S. Hu, Y. Chen, C.-M. Chan, W. Chen et al. , “Parameter-efficient fine-tuning of large-scale pre-trained language models,” Nature Machine Intelligence , vol. 5, no. 3, pp. 220–235, Mar. 2023

2023

Earlier work this paper cites.

Z. Zhang, Y. Yang, Y. Dai, Q. Wang, Y. Yu, L. Qu, and Z. Xu, “FedPETuning: When federated learning meets the parameter-efficient tuning methods of pre-trained language models,” in Findings of ACL , Toronto, Canada, July 2023, pp. 9963–9977

2023

Earlier work this paper cites.

E. Zelikman, Q. Huang, P. Liang, N. Haber, and N. D. Goodman, “Just one byte (per gradient): A note on low-bandwidth decentralized language model finetuning using shared randomness,” arXiv preprint arXiv:2306.10015 , 2023

Original

2023

Cited alongside, same era.

X. Ma, G. Fang, and X. Wang, “LLM-pruner: On the structural pruning of large language models,” in NeurIPS , vol. 36, New Orleans, LA, USA, Dec. 2023, pp. 21 702–21 720

2023

Cited alongside, same era.

E. Frantar, S. Ashkboos, T. Hoefler, and D. Alistarh, “OPTQ: Accurate quantization for generative pre-trained transformers,” in ICLR , Kigali, Rwanda, May 2023

2023

Cited alongside, same era.

E. Frantar and D. Alistarh, “SparseGPT: Massive language models can be accurately pruned in one-shot,” in ICML , Honolulu, HI, USA, July 2023, pp. 10 323–10 337

2023

Cited alongside, same era.

J. Zhang, S. Vahidian, M. Kuo, C. Li, R. Zhang, T. Yu, G. Wang, and Y. Chen, “Towards building the federatedGPT: Federated instruction tuning,” in IEEE ICASSP , Seoul, Republic of Korea, Mar. 2024, pp. 6915–6919

2024

Closest in time.

M. Xu, D. Cai, Y. Wu, X. Li, and S. Wang, “FwdLLM: Efficient federated finetuning of large language models with perturbed inferences,” in USENIX ATC , Santa Clara, CA, USA, July 2024, pp. 579–596

2024

Closest in time.

Z. Qin, D. Chen, B. Qian, B. Ding, Y. Li, and S. Deng, “Federated full-parameter tuning of billion-sized language models with communication cost under 18 kilobytes,” in ICML , Vienna, Austria, July 2024

2024

Closest in time.

R. Agarwal, N. Vieillard, Y. Zhou, P. Stanczyk, S. R. Garea, M. Geist, and O. Bachem, “On-policy distillation of language models: Learning from self-generated mistakes,” in ICLR , Vienna, Austria, May 2024

2024

Closest in time.