Related papers: TraCT: Disaggregated LLM Serving with CXL Shared M…

LLM serving is increasingly multi-tenant: the same deployment must handle latency-critical interactive requests and more relaxed background workloads under a fixed GPU budget. This creates a tiered-SLO setting where maximizing overall…

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…

Real-time LLM interactions demand streamed token generations, where text tokens are progressively generated and delivered to users while balancing two objectives: responsiveness (i.e., low time-to-first-token) and steady generation…

Global KV-cache sharing is an effective optimization for accelerating large language model (LLM) inference, yet it introduces an API-visible timing side channel that lets adversaries infer sensitive user inputs from shared entries, leading…

State-of-the-art federated learning methods can perform far worse than their centralized counterparts when clients have dissimilar data distributions. For neural networks, even when centralized SGD easily finds a solution that is…

The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed KV vectors. However, its memory consumption scales linearly…

Disaggregated memory (DM) separates compute and memory resources, allowing flexible scaling to achieve high resource utilization. To ensure atomic and consistent data access on DM, distributed transaction systems have been adapted, where…

Cross-attention is commonly adopted in multimodal large language models (MLLMs) for integrating visual information into the language backbone. However, in applications with large visual inputs, such as video understanding, processing a…

Memory disaggregation is being considered as a strong alternative to traditional architecture to deal with the memory under-utilization in data centers. Disaggregated memory can adapt to dynamically changing memory requirements for the data…

Large language model (LLM) applications often reuse previously processed context, such as chat history and documents, which introduces significant redundant computation. Existing LLM serving systems address such redundant computation by…

CXL (Compute Express Link) is an emerging open industry-standard interconnect between processing and memory devices that is expected to revolutionize the way systems are designed. It enables cache-coherent, shared memory pools in a…

Retrieval-Augmented Generation (RAG) systems suffer from severe time-to-first-token (TTFT) bottlenecks due to long input sequences. Existing KV cache reuse methods face a fundamental trade-off: prefix caching requires identical prefixes…

Large Language Models (LLMs) are increasingly deployed in complex multi-agent applications that rely on external function calls. This workload creates severe performance challenges for the KV Cache: spatial contention leads to the eviction…

Graph-based retrieval-augmented generation (RAG) enables large language models (LLMs) to incorporate structured knowledge via graph retrieval as contextual input, enhancing more accurate and context-aware reasoning. We observe that for…

Prefill-Decode (PD) disaggregation has become the standard architecture for modern LLM inference engines, which alleviates the interference of two distinctive workloads. With the growing demand for multi-turn interactions in chatbots and…

Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. This surge in demand poses significant challenges in optimizing throughput and latency while keeping costs manageable. The Key-Value…

During LLM inference, KVCache memory usage grows linearly with sequence length and batch size and often exceeds GPU capacity. Recent proposals offload KV states to host memory and reduce transfers using top-k attention. But their…

How to efficiently serve Large Language Models (LLMs) has become a pressing issue because of their huge computational cost in their autoregressive generation process. To mitigate computational costs, LLMs often employ the KV Cache technique…

Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications. However, their increased computational and memory demands present significant…

Recent large language models (LLMs) with enormous model sizes use many GPUs to meet memory capacity requirements incurring substantial costs for token generation. To provide cost-effective LLM inference with relaxed latency constraints,…