4 papers
Accelerating Mixture-of-Expert Inference with Adaptive Expert Split Mechanism
Jiaming Yan, Jianchun Liu, Hongli Xu +1
Mixture-of-Experts (MoE) has emerged as a promising architecture for modern large language models (LLMs). However, massive parameters impose heavy GPU memory (i.e., VRAM) demands,…
FedQuad: Adaptive Layer-wise LoRA Deployment and Activation Quantization for Federated Fine-Tuning
Rukuo Li, Jianchun Liu, Hongli Xu +1
Federated fine-tuning (FedFT) provides an effective paradigm for fine-tuning large language models (LLMs) in privacy-sensitive scenarios. However, practical deployment remains chal…
Efficient Federated Fine-Tuning of Large Language Models with Layer Dropout
Shilong Wang, Jianchun Liu, Hongli Xu +2
Fine-tuning plays a crucial role in enabling pre-trained LLMs to evolve from general language comprehension to task-specific expertise. To preserve user data privacy, federated fin…
Caesar: A Low-deviation Compression Approach for Efficient Federated Learning
Jiaming Yan, Jianchun Liu, Hongli Xu +4
Compression is an efficient way to relieve the tremendous communication overhead of federated learning (FL) systems. However, for the existing works, the information loss under com…