Related papers: FUSEE: A Fully Memory-Disaggregated Key-Value Stor…
Personalized medication aims to tailor healthcare to individual patient characteristics. However, the heterogeneity of patient data across healthcare systems presents significant challenges to achieving accurate and effective personalized…
Federated Learning (FL) has become a viable technique for realizing privacy-enhancing distributed deep learning on the network edge. Heterogeneous hardware, unreliable client devices, and energy constraints often characterize edge computing…
Scaling Federated Learning (FL) to billion-parameter models forces a challenging trade-off between privacy, scalability, and model utility. Existing solutions often tackle these challenges in isolation, sacrificing accuracy, relying on…
Mixture-of-Experts (MoE) models deliver high quality at low training FLOPs, but this efficiency often vanishes at inference. We identify a double penalty that structurally disadvantages MoE architectures during decoding: first, expert…
Factorised databases are relational databases that use compact factorised representations at the physical layer to reduce data redundancy and boost query performance. This paper introduces FDB, an in-memory query engine for…
Transformer models face scalability challenges in causal language modeling (CLM) due to inefficient memory allocation for growing key-value (KV) caches, which strains compute and storage resources. Existing methods like Grouped Query…
We address the problem of compactly storing a large number of versions (snapshots) of a collection of keyed documents or records in a distributed environment, while efficiently answering a variety of retrieval queries over those, including…
Sequential recommendation models are widely used in applications, yet they face stringent latency requirements. Mainstream models leverage the Transformer attention mechanism to improve performance, but its computational complexity grows…
Resource disaggregation offers a cost effective solution to resource scaling, utilization, and failure-handling in data centers by physically separating hardware devices in a server. Servers are architected as pools of processor, memory,…
Modern large language model (LLM) inference has progressively disaggregated to keep pace with growing model sizes and tight TTFT and TPOT service-level objectives: from chunked-prefill aggregation, to prefill-decode (P/D) disaggregation,…
Federated Unlearning (FU) is emerging as a powerful tool that enables the selective removal of client data to effectively address data contamination and meet strict privacy regulations in mobile edge computing (MEC) systems. Although FU has…
Memory disaggregation has attracted great attention recently because of its benefits in efficient memory utilization and ease of management. So far, memory disaggregation research has all taken one of two approaches: building/emulating…
Modern distributed storage systems often use erasure codes to protect against disk and node failures to increase reliability, while trying to meet the latency requirements of the applications and clients. Storage systems may have caches at…
Federated learning (FL) is a promising paradigm for training a global model over data distributed across multiple data owners without centralizing clients' raw data. However, sharing of local model updates can also reveal information of…
State-of-the-art distributed in-memory datastores (FaRM, FaSST, DrTM) provide strongly-consistent distributed transactions with high performance and availability. Transactions in those systems are fully general; they can atomically…
This paper introduces Distribution-Flexible Subset Quantization (DFSQ), a post-training quantization method for super-resolution networks. Our motivation for developing DFSQ is based on the distinctive activation distributions of current…
We exploit a general cluster-based network architecture for a fronthaul-limited user-centric cell-free massive multiple-input multiple-output (CF-mMIMO) system under different degrees of cooperation among the access points (APs) to achieve…
Multimodal large language models suffer from substantial inference overhead since multimodal KV Cache grows proportionally with the visual input length. Existing multimodal KV Cache compression methods mostly rely on attention score to…
Emerging Deep Learning (DL) applications introduce heavy I/O workloads on computer clusters. The inherent long lasting, repeated, and random file access pattern can easily saturate the metadata and data service and negatively impact other…
Federated Learning (FL) enables collaborative model training without sharing raw data but suffers from limited scalability, high communication costs, and privacy risks due to its centralized architecture. This paper proposes FedSelect-ME, a…