Trinity: Disaggregating Vector Search from Prefill-Decode Disaggregation in LLM Serving

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Yi, Qian, Chen
Format:	Preprint
Published:	2025
Subjects:	Databases
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Efficient Vector Search on Disaggregated Memory with d-HNSW
by: Liu, Yi, et al.
Published: (2025)

d-HNSW: A High-performance Vector Search Engine on Disaggregated Memory
by: Fang, Fei, et al.
Published: (2026)

Nexus:Proactive Intra-GPU Disaggregation of Prefill and Decode in LLM Serving
by: Shi, Xiaoxiang, et al.
Published: (2025)

Prefill-Decode Aggregation or Disaggregation? Unifying Both for Goodput-Optimized LLM Serving
by: Wang, Chao, et al.
Published: (2025)

DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving
by: Zhong, Yinmin, et al.
Published: (2024)

Outback: Fast and Communication-efficient Index for Key-Value Store on Disaggregated Memory
by: Liu, Yi, et al.
Published: (2025)

Disaggregated Database Management Systems
by: Ghandeharizadeh, Shahram, et al.
Published: (2024)

Not All Prefills Are Equal: PPD Disaggregation for Multi-turn LLM Serving
by: Li, Zongze, et al.
Published: (2026)

SPAD: Specialized Prefill and Decode Hardware for Disaggregated LLM Inference
by: Zhang, Hengrui, et al.
Published: (2025)

PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated Serving
by: Woo, Sunghyeon, et al.
Published: (2026)

SHINE: A Scalable HNSW Index in Disaggregated Memory
by: Widmoser, Manuel, et al.
Published: (2025)

PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference
by: Zhang, Hao, et al.
Published: (2025)

Disaggregated Prefill and Decoding Inference System for Large Language Model Serving on Multi-Vendor GPUs
by: Chen, Xing, et al.
Published: (2025)

VIDEX: A Disaggregated and Extensible Virtual Index for the Cloud and AI Era
by: Kang, Rong, et al.
Published: (2025)

Cache Coherence Over Disaggregated Memory
by: Wang, Ruihong, et al.
Published: (2024)

SLO-Aware Compute Resource Allocation for Prefill-Decode Disaggregated LLM Inference
by: Li, Luchang, et al.
Published: (2026)

OffloadFS: Leveraging Disaggregated Storage for Computation Offloading
by: Moon, Sungho, et al.
Published: (2026)

DEX: Scalable Range Indexing on Disaggregated Memory [Extended Version]
by: Lu, Baotong, et al.
Published: (2024)

Evolution of Buffer Management in Database Systems: From Classical Algorithms to Machine Learning and Disaggregated Memory
by: Gadupudi, Prudhvi, et al.
Published: (2025)

O^3-LSM: Maximizing Disaggregated LSM Write Performance via Three-Layer Offloading
by: Lin, Qi, et al.
Published: (2026)

CIDER: Boosting Memory-Disaggregated Key-Value Stores with Pessimistic Synchronization
by: Du, Yuxuan, et al.
Published: (2026)

Spatially Disaggregated Energy Consumption and Emissions in End-use Sectors for Germany and Spain
by: Patil, Shruthi, et al.
Published: (2025)

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference
by: Tang, Xiaojuan, et al.
Published: (2025)

DUET: Disaggregated Hybrid Mamba-Transformer LLMs with Prefill and Decode-Specific Packages
by: Kanani, Alish, et al.
Published: (2026)

RelServe: Fast LLM Inference Serving on Relational Data
by: Zhang, Xin, et al.
Published: (2025)

Cronus: Efficient LLM inference on Heterogeneous GPU Clusters via Partially Disaggregated Prefill
by: Liu, Yunzhao, et al.
Published: (2025)

DynaServe: Unified and Elastic Execution for Dynamic Disaggregated LLM Serving
by: Ruan, Chaoyi, et al.
Published: (2025)

MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool
by: Hu, Cunchen, et al.
Published: (2024)

The Virtuous Cycle: AI-Powered Vector Search and Vector Search-Augmented AI
by: Wei, Jiuqi, et al.
Published: (2026)

TigerVector: Supporting Vector Search in Graph Databases for Advanced RAGs
by: Liu, Shige, et al.
Published: (2025)

Stream2LLM: Overlap Context Streaming and Prefill for Reduced Time-to-First-Token (TTFT)
by: Bachkaniwala, Rajveer, et al.
Published: (2026)

HARMONY: A Scalable Distributed Vector Database for High-Throughput Approximate Nearest Neighbor Search
by: Xu, Qian, et al.
Published: (2025)

Cracking Vector Search Indexes
by: Mageirakos, Vasilis, et al.
Published: (2025)

Optimizing SSD-Resident Graph Indexing for High-Throughput Vector Search
by: Zhao, Weichen, et al.
Published: (2026)

StreamServe: Adaptive Speculative Flows for Low-Latency Disaggregated LLM Serving
by: Kumar, Satyam, et al.
Published: (2026)

Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
by: Qin, Ruoyu, et al.
Published: (2024)

Efficient Multi-round LLM Inference over Disaggregated Serving
by: He, Wenhao, et al.
Published: (2026)

Approximate Vector Set Search Inspired by Fly Olfactory Neural System
by: Li, Yiqi, et al.
Published: (2024)

The CAP Principle for LLM Serving: A Survey of Long-Context Large Language Model Serving
by: Zeng, Pai, et al.
Published: (2024)

GreenLLM: Disaggregating Large Language Model Serving on Heterogeneous GPUs for Lower Carbon Emissions
by: Shi, Tianyao, et al.
Published: (2024)