Related papers: Trinity: Disaggregating Vector Search from Prefill…

The rapid adoption of AI and convenience offered by cloud services have resulted in the growing demands for GPUs in the cloud. Generally, GPUs are physically attached to host servers as PCIe devices. However, the fixed assembly combination…

Vector search (VS) is now available in most database engines. However, while vector search is a common feature in AI/ML/LLMs where the dominant computing platforms are GPUs, existing database engines operate on CPUs even when implementing…

Serving Large Language Models (LLMs) is a GPU-intensive task where traditional autoscalers fall short, particularly for modern Prefill-Decode (P/D) disaggregated architectures. This architectural shift, while powerful, introduces…

Prefill/decode disaggregation is increasingly adopted in LLM serving to improve the latency-throughput tradeoff and meet strict TTFT and TPOT SLOs. However, LLM inference remains energy-hungry: autoscaling alone is too coarse-grained to…

Large Language Models (LLMs) have gained popularity in recent years, driving up the demand for inference. LLM inference is composed of two phases with distinct characteristics: a compute-bound prefill phase followed by a memory-bound decode…

A Retrieval-Augmented Language Model (RALM) combines a large language model (LLM) with a vector database to retrieve context-specific knowledge during text generation. This strategy facilitates impressive generation quality even with…

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…

Each request in LLM inference goes through two phases: compute-bound prefill and memory-bandwidth-bound decode. To improve GPU utilization, recent systems use hybrid batching that combines the prefill and decode phases of different requests…

Disaggregating the prefill and decoding phases represents an effective new paradigm for generative inference of large language models (LLM), which eliminates prefill-decoding interference and optimizes resource allocation. However, it is…

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,…

Large Language Models (LLMs) for code generation can replicate insecure patterns from their training data. To mitigate this, a common strategy for security hardening is to fine-tune models using supervision derived from the final…

The architectural shift to prefill/decode (PD) disaggregation in LLM serving improves resource utilization but struggles with the bursty nature of modern workloads. Existing autoscaling policies, often retrofitted from monolithic systems…

Multimodal large language models (LLMs) empower LLMs to ingest inputs and generate outputs in multiple forms, such as text, image, and audio. However, the integration of multiple modalities introduces heterogeneity in both the model and…

Although Multi-Vector Retrieval (MVR) has achieved the state of the art on many information retrieval (IR) tasks, its performance highly depends on how to decompose queries into smaller pieces, say phrases or tokens. However, optimizing…

Vector similarity search has become a critical component in AI-driven applications such as large language models (LLMs). To achieve high recall and low latency, GPUs are utilized to exploit massive parallelism for faster query processing.…

There is an increasing adoption of machine learning for encoding data into vectors to serve online recommendation and search use cases. As a result, recent data management systems propose augmenting query processing with online vector…

Processing moving object trajectories arises in many application domains and has been addressed by practitioners in the spatiotemporal database and Geographical Information System communities. In this work, we focus on a trajectory…

Large Language Models (LLMs) are rapidly becoming critical infrastructure for enterprise applications, driving unprecedented demand for GPU-based inference services. A key operational challenge arises from the two-phase nature of LLM…

As the model size continuously increases, pipeline parallelism shows great promise in throughput-oriented LLM inference due to its low demand on communications. However, imbalanced pipeline workloads and complex data dependencies in the…

Disaggregation has emerged as a powerful strategy for optimizing large language model (LLM) inference by separating compute-intensive prefill and memory-bound decode phases across specialized GPUs. This separation improves utilization and…