11 papers
Pallas: A Proactive KV Cache Migration Framework for LLM Inference in AI-RAN
Tianhang Ding, Jianchun Liu, Hongli Xu
AI-RAN brings large language model (LLM) serving close to mobile users, but cellular handover can separate an active request from its inference state: the user attaches to a target…
Bandwidth-Aware and Cost-Efficient Pipeline Parallel Scheduling in Geo-Distributed LLM Training
Han Zhang, Jianchun Liu, Hongli Xu
The rapid evolution of large language models (LLMs) has made geographically distributed training necessary due to GPU scarcity within a single cloud region. In such cross-region se…
Adaptive and Fine-grained Module-wise Expert Pruning for Efficient LoRA-MoE Fine-Tuning
Weihang Li, Jianchun Liu, Hongli Xu
LoRA-MoE has emerged as an effective paradigm for parameter-efficient fine-tuning, combining the low training cost of LoRA with the increased adaptation capacity of Mixture-of-Expe…
Improving LLM Reasoning via Dependency-Aware Query Decomposition and Logic-Parallel Content Expansion
Xianjun Gao, Jianchun Liu, Hongli Xu +1
The integration of Large Language Models (LLMs) into real-time Web applications, such as AI-powered search and conversational agents, presents a fundamental Web infrastructure chal…
SABlock: Semantic-Aware KV Cache Eviction with Adaptive Compression Block Size
Jinhan Chen, Jianchun Liu, Hongli Xu +2
The growing memory footprint of the Key-Value (KV) cache poses a severe scalability bottleneck for long-context Large Language Model (LLM) inference. While KV cache eviction has em…
Towards Communication-Efficient Decentralized Federated Graph Learning over Non-IID Data
Shilong Wang, Jianchun Liu, Hongli Xu +3
Decentralized Federated Graph Learning (DFGL) overcomes potential bottlenecks of the parameter server in FGL by establishing a peer-to-peer (P2P) communication network among worker…
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,…
Adaptive KV-Cache Compression without Manually Setting Budget
Chenxia Tang, Jianchun Liu, Hongli Xu +1
Large language models (LLMs) inference relies heavily on KV-caches to accelerate autoregressive decoding, but the resulting memory footprint grows rapidly with sequence length, pos…
Air-FedGA: A Grouping Asynchronous Federated Learning Mechanism Exploiting Over-the-air Computation
Qianpiao Ma, Junlong Zhou, Xiangpeng Hou +4
Federated learning (FL) is a new paradigm to train AI models over distributed edge devices (i.e., workers) using their local data, while confronting various challenges including co…
Mitigating Catastrophic Forgetting with Adaptive Transformer Block Expansion in Federated Fine-Tuning
Yujia Huo, Jianchun Liu, Hongli Xu +3
Federated fine-tuning (FedFT) of large language models (LLMs) has emerged as a promising solution for adapting models to distributed data environments while ensuring data privacy.…
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…