ForkKV: Scaling Multi-LoRA Agent Serving via Copy-on-Write Disaggregated KV Cache

• URL: http://arxiv.org/abs/2604.06370v1
• Date: Tue, 07 Apr 2026 18:52:25 GMT
• Title: ForkKV: Scaling Multi-LoRA Agent Serving via Copy-on-Write Disaggregated KV Cache
• Abstract summary: Low-Rank Adaptation (LoRA) introduces a critical memory footprint bottleneck during serving.<n>By exploiting the structural properties of LoRA, ForkKV physically decouples the KV cache into a massive shared component.<n>We show that ForkKV achieves up to 3.0x the throughput of state-of-the-art multi-LoRA serving systems.
• Score: 8.323914332215598
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The serving paradigm of large language models (LLMs) is rapidly shifting towards complex multi-agent workflows where specialized agents collaborate over massive shared contexts. While Low-Rank Adaptation (LoRA) enables the efficient co-hosting of these specialized agents on a single base model, it introduces a critical memory footprint bottleneck during serving. Specifically, unique LoRA activations cause Key-Value (KV) cache divergence across agents, rendering traditional prefix caching ineffective for shared contexts. This forces redundant KV cache maintenance, rapidly saturating GPU capacity and degrading throughput. To address this challenge, we introduce ForkKV, a serving system for multi-LoRA agent workflows centered around a novel memory management paradigm in OS: fork with copy-on-write (CoW). By exploiting the structural properties of LoRA, ForkKV physically decouples the KV cache into a massive shared component (analogous to the parent process's memory pages) and lightweight agent-specific components (the child process's pages). To support this mechanism, we propose a DualRadixTree architecture that allows newly forked agents to inherit the massive shared cache and apply CoW semantics for their lightweight unique cache. Furthermore, to guarantee efficient execution, we design ResidualAttention, a specialized kernel that reconstructs the disaggregated KV cache directly within on-chip SRAM. Comprehensive evaluations across diverse language models and practical datasets of different tasks demonstrate that ForkKV achieves up to 3.0x the throughput of state-of-the-art multi-LoRA serving systems with a negligible impact on generation quality.

Related papers

• Tangram: Unlocking Non-Uniform KV Cache for Efficient Multi-turn LLM Serving [12.478756445519409]
  Tangram is a novel serving system designed to make Non-uniform KV caches practical.<n>Tangram improves throughput by up to 2.6x compared to existing baselines.
  arXiv  Detail & Related papers  (2026-06-04T15:41:27Z)
• ICaRus: Identical Cache Reuse for Efficient Multi Model Inference [14.040073161061578]
  ICaRus is a novel architecture that allows multiple models to share identical KV caches across all layers.<n>ICaRus achieves up to 11.1x lower P95 latency and 3.8x higher throughput in multi agent workflow with 8 different models.
  arXiv  Detail & Related papers  (2026-02-27T14:21:45Z)
• DeltaKV: Residual-Based KV Cache Compression via Long-Range Similarity [50.52392445266824]
  We propose a residual-based KV cache compression framework motivated by long-range inter-token similarity and highly shared latent components in KV representations.<n>Instead of discarding tokens, DeltaKV encodes semantic residuals relative to retrieved historical references, preserving fidelity while substantially reducing storage.<n>Experiments show that DeltaKV reduces KV cache memory to 29% of the original while maintaining near-lossless accuracy on LongBench, SCBench, and AIME.
  arXiv  Detail & Related papers  (2026-02-08T15:14:36Z)
• LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents [9.162948089580143]
  We propose LRAgent, a KV cache sharing framework for multi-LoRA agents.<n> LRAgent decomposes the cache into a shared base component from the pretrained weights and an adapter-dependent component from LoRA weights.<n> LRAgent achieves throughput and time-to-first-token latency close to fully shared caching.
  arXiv  Detail & Related papers  (2026-02-01T06:36:46Z)
• Joint Encoding of KV-Cache Blocks for Scalable LLM Serving [3.3230675313521716]
  Existing KV-cache compression methods rely on rigids, disrupt tensor layouts, or require specialized compute.<n>We propose joint encoding of KV-cache blocks, which fuses similar blocks across requests and input chunks into shared representations.<n>This alleviates the KV-cache memory bottleneck, supporting high-concurrency serving without specialized hardware.
  arXiv  Detail & Related papers  (2026-01-06T14:50:58Z)
• KVShare: An LLM Service System with Efficient and Effective Multi-Tenant KV Cache Reuse [17.301289617498448]
  We present a KV cache management module that shares the KV cache across requests under multi-tenant scenarios.<n> KVShare reduces TTFT by up to 9.39x and increases 1.2x of the throughput compared to the full KV recompute.<n> KVShare achieves 20.38% boost in terms of accuracy compared to SOTA methods.
  arXiv  Detail & Related papers  (2025-03-17T16:43:35Z)
• QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache [67.84112700032007]
  Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings.<n>In these scenarios, the Key-Value ( KV) cache is the primary bottleneck in terms of both GPU memory and latency.<n>We propose a novel self-speculative decoding framework, QuantSpec, where the draft model shares the architecture of the target model but employs a hierarchical 4-bit quantized KV cache and 4-bit quantized weights for acceleration.
  arXiv  Detail & Related papers  (2025-02-05T20:43:48Z)
• CSR:Achieving 1 Bit Key-Value Cache via Sparse Representation [63.65323577445951]
  We propose a novel approach called Cache Sparse Representation (CSR)<n>CSR transforms the dense Key-Value cache tensor into sparse indexes and weights, offering a more memory-efficient representation during LLM inference.<n>Our experiments demonstrate CSR achieves performance comparable to state-of-the-art KV cache quantization algorithms.
  arXiv  Detail & Related papers  (2024-12-16T13:01:53Z)
• SCBench: A KV Cache-Centric Analysis of Long-Context Methods [61.025422435235456]
  We introduce SCBench, a benchmark for evaluating long-context methods from a KV cachecentric perspective.<n>We provide an extensive KV cache-centric analysis of eight categories long-context solutions, including Gated Linear RNNs and Mamba-Attention hybrids.<n>Our findings show that sub-O(n) memory methods suffer in multi-turn scenarios, while sparse encoding with O(n) memory and sub-O(n2) pre-filling perform robustly.
  arXiv  Detail & Related papers  (2024-12-13T17:59:52Z)
• Lossless KV Cache Compression to 2% [22.98828332096935]
  This work introduces a novel architecture, Cross-Layer Latent Attention (CLLA), aimed at compressing the KV cache to less than 2% of its original size. CLLA integrates attention head/dimension reduction, layer sharing, and quantization techniques, into a cohesive framework.
  arXiv  Detail & Related papers  (2024-10-20T02:17:35Z)
• ThinK: Thinner Key Cache by Query-Driven Pruning [63.13363917871414]
  Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications.<n>This paper focuses on the long-context scenario, addressing the inefficiencies in KV cache memory consumption during inference.<n>We propose ThinK, a novel query-dependent KV cache pruning method designed to minimize attention weight loss while selectively pruning the least significant channels.
  arXiv  Detail & Related papers  (2024-07-30T17:59:08Z)
• Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs [82.08922896531618]
  We introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs) We conduct targeted profiling to discern the intrinsic structure of attention modules. Based on the recognized structure, we then construct the KV cache in an adaptive manner: evicting long-range contexts on attention heads emphasizing local contexts, discarding non-special tokens on attention heads centered on special tokens, and only employing the standard KV cache for attention heads that broadly attend to all tokens.
  arXiv  Detail & Related papers  (2023-10-03T05:17:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.