Search for: All records

Award ID contains: 2420632

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Efficient vector search is essential for powering large-scale AI applications, such as LLMs. Existing solutions are designed for monolithic architectures where compute and memory are tightly coupled. Recently, disaggregated architecture breaks this coupling by separating computation and memory resources into independently scalable pools to improve utilization. However, applying vector database to a disaggregated memory system brings unique challenges to system design due to its graph-based index. We present d-HNSW, the first RDMA-based vector search engine optimized for disaggregated memory systems. d-HNSW preserves HNSW's high accuracy while addressing the new system-level challenges introduced by disaggregation: 1) network inefficiency from pointer-chasing traversals, 2) non-contiguous remote memory layout induced by dynamic insertions, 3) redundant data transfers in batch workloads, and 4) resource underutilization due to sequential execution. d-HNSW tackles these challenges through a set of hardware-algorithm co-designed techniques, including 1) balanced clustering with a lightweight representative index to reduce network round-trips and ensure predictable latency, 2) an RDMA-friendly graph layout that preserves data contiguity under dynamic insertions, 3) query-aware data loading to eliminate redundant fetches across batch queries, and 4) a pipelined execution model that overlaps RDMA transfers with computation to hide network latency and improve throughput. Our evaluation results in a public cloud show that d-HNSW achieves up to < 10-2× query latency and >100× query throughput compared to other baselines, while maintaining a high recall of 94%. 
    more » « less
    Free, publicly-accessible full text available May 29, 2027
  2. While significant progress has been made in research and development on open-source and cost-efficient large-language models (LLMs), serving scalability remains a critical challenge, particularly for small organizations and individuals seeking to deploy and test their LLM innovations. Inspired by peer-to-peer networks that leverage decentralized overlay nodes to increase throughput and availability, we propose PlanetServe, an LLM serving overlay that harnesses computing resources from decentralized contributors. We identify four key research problems inherent to enabling such a decentralized infrastructure: 1) overlay network organization; 2) LLM communication privacy; 3) overlay forwarding for resource efficiency; and 4) verification of serving quality. This work presents the first systematic study of these fundamental problems in the context of decentralized LLM serving. Evaluation results from a prototype implemented on a set of decentralized nodes demonstrate that PlanetServe achieves a latency reduction of over 50% compared to the baseline design without overlay forwarding. Furthermore, the security features introduce minimal overhead to serving latency and throughput. We believe this work pioneers a new direction for democratizing and scaling future AI serving capabilities. 
    more » « less
    Free, publicly-accessible full text available May 1, 2027
  3. Free, publicly-accessible full text available January 1, 2027
  4. Disaggregated memory systems achieve resource utilization efficiency and system scalability by distributing computation and memory resources into distinct pools of nodes. RDMA is an attractive solution to support high-throughput communication between different disaggregated resource pools. However, existing RDMA solutions face a dilemma: one-sided RDMA completely bypasses computation at memory nodes, but its communication takes multiple round trips; two-sided RDMA achieves one-round-trip communication but requires non-trivial computation for index lookups at memory nodes, which violates the principle of disaggregated memory. This work presents Outback, a novel indexing solution for key-value stores with a one-round-trip RDMA-based network that does not incur computation-heavy tasks at memory nodes. Outback is the first to utilize dynamic minimal perfect hashing and separates its index into two components: one memory-efficient and compute-heavy component at compute nodes and the other memory-heavy and compute-efficient component at memory nodes. We implement a prototype of Outback and evaluate its performance in a public cloud. The experimental results show that Outback achieves higher throughput than both the state-of-the-art one-sided RDMA and two-sided RDMA-based in-memory KVS by 1.06--5.03×, due to the unique strength of applying a separated perfect hashing index. 
    more » « less