Related papers: FlexKV: Flexible Index Offloading for Memory-Disag…

The deployment of efficient long-context LLMs in applications like autonomous agents, long-chain reasoning, and creative writing is fundamentally bottlenecked by the linear growth of KV cache memory. Existing compression and eviction…

Large language models have revolutionized natural language processing, yet their deployment remains hampered by the substantial memory and runtime overhead of the transformer's Key-Value cache. To mitigate this, recent methods employ a…

Diffusion Language Models (DLMs) have been seen as a promising competitor for autoregressive language models. However, diffusion language models have long been constrained by slow inference. A core challenge is that their non-autoregressive…

Auto-regressive inference of transformers benefit greatly from Key-Value (KV) caching, but can lead to major memory bottlenecks as model size, batch size, and sequence length grow at scale. We introduce Multi-Layer Key-Value (MLKV) sharing,…

Disaggregated LLM serving improves resource efficiency by separating the compute-intensive prefill phase from the latency-critical decode phase. However, this architecture introduces a fundamental bottleneck: key/value (KV) tensors…

Long-horizon LLM inference turns the key--value (KV) cache into the dominant GPU memory consumer and makes per-token attention increasingly expensive. Many common eviction policies use static recency windows or historical attention, leaving…

Large Language Model (LLM) inference is increasingly constrained by memory bandwidth, with frequent access to the key-value (KV) cache dominating data movement. While attention sparsity reduces some memory traffic, the relevance of past…

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…

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…

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…

Key-value (KV) caching is critical for efficient inference in large language models (LLMs), yet its memory footprint scales linearly with context length, resulting in a severe scalability bottleneck. Existing approaches largely treat KV…

LLMs are widely adopted in production, pushing inference systems to their limits. Disaggregated LLM serving (e.g., PD separation and KV state disaggregation) improves scalability and cost efficiency, but it also turns KV into an explicit…

Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving. Current systems suffer from three compounding inefficiencies: (1) the absence of unified KV cache…

Distributed LLM serving is costly and often underutilizes hardware accelerators due to three key challenges: bubbles in pipeline-parallel deployments caused by the bimodal latency of prompt and token processing, GPU memory overprovisioning,…

Large language models (LLMs) are widely deployed with rapidly expanding context windows to support increasingly demanding applications. However, long contexts pose significant deployment challenges, primarily due to the KV cache whose size…

Long-context Large Language Models (LLMs) enable powerful applications but incur high memory costs due to the key-value states (KV-Cache). Recent studies attempt to share KV-Cache across layers, but these approaches either require expensive…

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) serving is increasingly constrained by the growing size of the key-value (KV) cache, which scales with both context length and generation length. Prior work shows that attention is dominated by a small subset of…

As large-scale language models continue to scale up in both size and context length, the memory and communication cost of key-value (KV) cache storage has become a major bottleneck in multi-GPU and multi-node inference. While MoE-based…

As Large Language Models (LLMs) scale to support context windows exceeding one million tokens, the linear growth of Key-Value (KV) cache imposes severe memory capacity and bandwidth bottlenecks, constraining the efficiency of long-context…