Related papers: FUSEE: A Fully Memory-Disaggregated Key-Value Stor…

Disaggregated memory (DM) is a promising data center architecture that decouples CPU and memory into independent resource pools to improve resource utilization. Building on DM, memory-disaggregated key-value (KV) stores are adopted to…

Transformer decoders have achieved strong results across tasks, but the memory required for the KV cache becomes prohibitive at long sequence lengths. Although Cross-layer KV Cache sharing (e.g., YOCO, CLA) offers a path to mitigate KV…

Persistent key-value (KV) stores are critical infrastructure for data-intensive applications. Leveraging high-performance Non-Volatile Memory (NVM) to enhance KV stores has gained traction. However, previous work has primarily focused on…

Modern large-scale services such as search engines, messaging platforms, and serverless functions, rely on key-value (KV) stores to maintain high performance at scale. When such services are deployed in constrained memory environments, they…

Memory-disaggregated key-value (KV) stores suffer from a severe performance bottleneck due to their I/O redundancy issues. A huge amount of redundant I/Os are generated when synchronizing concurrent data accesses, making the limited network…

Cloud key-value (KV) stores provide businesses with a cost-effective and adaptive alternative to traditional on-premise data management solutions. KV stores frequently consist of heterogeneous clusters, characterized by varying hardware…

Mixture-of-Experts (MoE) models offer high capacity with efficient inference cost by activating a small subset of expert models per input. However, deploying MoE models requires all experts to reside in memory, creating a gap between the…

Cloud platforms host thousands of tenants that demand POSIX semantics, high throughput, and rapid evolution from their storage layer. Kernel-native distributed file systems supply raw speed, but their privileged code base couples every…

Disaggregated inference has become an essential framework that separates the prefill (P) and decode (D) stages in large language model inference to improve throughput. However, the KV cache transfer faces significant delays between prefill…

Federated Learning (FL) is an approach for privacy-preserving Machine Learning (ML), enabling model training across multiple clients without centralized data collection. With an aggregator server coordinating training, aggregating model…

Caches at CPU nodes in disaggregated memory architectures amortize the high data access latency over the network. However, such caches are fundamentally unable to improve performance for workloads requiring pointer traversals across linked…

Different from traditional Large Language Model (LLM) serving that colocates the prefill and decode stages on the same GPU, disaggregated serving dedicates distinct GPUs to prefill and decode workload. Once the prefill GPU completes its…

Memory disaggregation is an emerging data center architecture that improves resource utilization and scalability. Replication is key to ensure the fault tolerance of applications, but replicating shared data in disaggregated memory is hard.…

Cloud deployments disaggregate storage from compute, providing more flexibility to both the storage and compute layers. In this paper, we explore disaggregation by taking it one step further and applying it to memory (DRAM). Disaggregated…

The disaggregated memory (DM) architecture offers high resource elasticity at the cost of data access performance. While caching frequently accessed data in compute nodes (CNs) reduces access overhead, it requires costly centralized…

Federated Learning (FL) is an emerging machine learning paradigm that enables the collaborative training of a shared global model across distributed clients while keeping the data decentralized. Recent works on designing systems for…

Deduplication has been largely employed in distributed storage systems to improve space efficiency. Traditional deduplication research ignores the design specifications of shared-nothing distributed storage systems such as no central…

Federated learning (FL) is a collaborative machine learning approach that enables multiple clients to train models without sharing their private data. With the rise of deep learning, large-scale models have garnered significant attention…

We present Dinomo, a novel key-value store for disaggregated persistent memory (DPM). Dinomo is the first key-value store for DPM that simultaneously achieves high common-case performance, scalability, and lightweight online…

Large language models (LLMs) demonstrate remarkable capabilities but face substantial serving costs due to their high memory demands, with the key-value (KV) cache being a primary bottleneck. State-of-the-art KV cache compression…