3 papers
cs.LG2025
MoE-Compression: How the Compression Error of Experts Affects the Inference Accuracy of MoE Model?
Songkai Ma, Zhaorui Zhang, Sheng Di +4
With the widespread application of Mixture of Experts (MoE) reasoning models in the field of LLM learning, efficiently serving MoE models under limited GPU memory constraints has e…
cs.DC2025
HLoRA: Efficient Federated Learning System for LLM Heterogeneous Fine-Tuning
Qianli Liu, Zhaorui Zhang, Xin Yao +1
Federated learning systems have been identified as an efficient approach to scaling distributed model training with a large amount of participants or data owners while guaranteeing…
cs.LG2025
CLLoRA: An Approach to Measure the Effects of the Context Length for LLM Fine-Tuning
Ping Zhang, Zhaorui Zhang, Sheng Di +2
Large language model fine-tuning has been identified as an efficient approach to applying the pre-trained Large language models to other domains. To guarantee data privacy for diff…