Introduces a three-tier architecture with an agent runtime layer and four primitives for agent-aware policies in LLM serving, validated on KV caching via CacheSage showing 13-37pp hit-rate gains on five workloads.
TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
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 of critical agents' caches and temporal underutilization leaves the cache of agents stalled on long-running function calls idling in GPU memory. We present TokenCake, a KV-Cache-centric serving framework that bridges this gap by co-optimizing scheduling and memory management through an agent-aware design. TokenCake's Temporal Scheduler employs an event-driven, opportunistic policy to proactively offload idle KV Caches during function calls and uses predictive uploading to hide data transfer latency. TokenCake's Spatial Scheduler uses dynamic memory partitioning, guided by a hybrid priority metric combining graph structure and runtime state, to reserve GPU memory for critical-path agents. Our evaluation on representative multi-agent benchmarks shows that TokenCake reduces end-to-end latency by over 47.06% and improves effective GPU memory utilization by up to 16.9% compared to vLLM.
citation-role summary
background 3
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 3polarities
background 3representative citing papers
Hive is a multi-agent infrastructure with a logits cache for reducing cross-path redundancy in sampling and agent-aware scheduling for better compute and KV-cache allocation, shown to deliver 1.11x-1.76x speedups and 33%-51% lower hotspot miss rates.
Scepsy schedules arbitrary multi-LLM agentic workflows on GPU clusters by constructing Aggregate LLM Pipelines from stable per-LLM execution time shares, then searching fractional GPU allocations, tensor parallelism, and replica counts to achieve up to 2.4x higher throughput and 27x lower latency.
ForkKV uses copy-on-write disaggregated KV cache with DualRadixTree and ResidualAttention kernels to deliver up to 3x throughput over prior multi-LoRA serving systems with negligible quality loss.
TokenDance scales multi-agent LLM serving to 2.7x more concurrent agents by collective KV cache reuse and block-sparse diff encoding that achieves 11-17x compression.
AsymCache combines Multi-Segment Attention, position-aware eviction, and adaptive chunking to cut TTFT by up to 2.03x and TPOT by up to 1.71x versus recent baselines in LLM serving.
Libra optimizes GPU allocation across rollout and training in agentic RL via an elastic hybrid pool and C-MLFQ scheduler based on tool-return causal signals, claiming up to 3.0x throughput and 2.5x faster reward convergence on 48 A800 GPUs.
citing papers explorer
-
A Policy-Driven Runtime Layer for Agentic LLM Serving
Introduces a three-tier architecture with an agent runtime layer and four primitives for agent-aware policies in LLM serving, validated on KV caching via CacheSage showing 13-37pp hit-rate gains on five workloads.
-
Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling
Hive is a multi-agent infrastructure with a logits cache for reducing cross-path redundancy in sampling and agent-aware scheduling for better compute and KV-cache allocation, shown to deliver 1.11x-1.76x speedups and 33%-51% lower hotspot miss rates.
-
Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines
Scepsy schedules arbitrary multi-LLM agentic workflows on GPU clusters by constructing Aggregate LLM Pipelines from stable per-LLM execution time shares, then searching fractional GPU allocations, tensor parallelism, and replica counts to achieve up to 2.4x higher throughput and 27x lower latency.
-
ForkKV: Scaling Multi-LoRA Agent Serving via Copy-on-Write Disaggregated KV Cache
ForkKV uses copy-on-write disaggregated KV cache with DualRadixTree and ResidualAttention kernels to deliver up to 3x throughput over prior multi-LoRA serving systems with negligible quality loss.
-
TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing
TokenDance scales multi-agent LLM serving to 2.7x more concurrent agents by collective KV cache reuse and block-sparse diff encoding that achieves 11-17x compression.
-
Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model Serving
AsymCache combines Multi-Segment Attention, position-aware eviction, and adaptive chunking to cut TTFT by up to 2.03x and TPOT by up to 1.71x versus recent baselines in LLM serving.
-
Libra: Efficient Resource Management for Agentic RL Post-Training
Libra optimizes GPU allocation across rollout and training in agentic RL via an elastic hybrid pool and C-MLFQ scheduler based on tool-return causal signals, claiming up to 3.0x throughput and 2.5x faster reward convergence on 48 A800 GPUs.