arXiv subjects

Zhuohang Bian

Publications and source records attributed to Zhuohang Bian.

5 recordsLinked to original sources

arXiv2026

HBF Sucks? A Full-Stack Characterization of High-Bandwidth Flash for KV-Centric LLM Serving

A faster storage device should make serving faster. We find the opposite. High-Bandwidth Flash (HBF) stacks NAND behind a wide, package-local interface, promising flash-scale capacity with far lower read latency and higher bandwidth than an SSD. The obvious move is to keep an SSD-style Mooncake KV-offloading stack and swap in HBF underneath. We built that system and measured it: an extended TokenSim, four complete two-hour Qwen-Bailian production traces, five dense and mixture-of-experts models, and H100/B200 profiles. The upgrade backfires. Average end-to-end latency rises 2--5.5$\times$ and maximum SLO goodput falls 1.1--2.7$\times$ across H100 and B200, so the faster device yields a slower system. A cost-benefit model explains the paradox: a faster far tier pays off only when read I/O is the bottleneck, reads outweigh writes, and delivered bandwidth is sustainable. Transient KV violates all three at once. Buying flash through the package costs GPU near-tier capacity and bandwidth, while HBF's own read/write latency barely matters: scaling it 3.75$\times$ moves latency less than 1\%. Worse, the two-tier hierarchy keeps reuse in the near tier and hands HBF a relentless write-heavy stream. Writes outnumber reads on every trace, so a 3D-ICE model shows the stack hits its thermal limit well below peak bandwidth, and a TLC tier wears out sooner than the SSD pool it replaced. The device is fine; the drop-in deployment is not. HBF sucks as an SSD replacement for transient KV, but earns its place in LLM serving when used selectively with reuse-aware placement, write budgeting, and thermal coordination.

cs.AR↗

arXiv2026

TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications

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.

cs.DC↗

arXiv2026

TokenStack: A Heterogeneous HBM-PIM Architecture and Runtime for Efficient LLM Inference

Large language model (LLM) serving is now limited by the key-value (KV) cache. During decode, each new token rereads prior KV state, so attention becomes a bandwidth- and capacity-heavy memory task. HBM-PIM helps by moving attention closer to memory, but current stack organizations still waste resources. In practice, only hot KV blocks benefit from near-memory compute. Weights, activations, and cold KV mainly need dense storage and GPU-visible bandwidth. A uniform HBM-PIM stack makes all layers pay for PIM logic, while a dedicated-PIM design such as AttAcc recovers capacity but shrinks the HBM bandwidth left for GPU-side work. We propose TokenStack, a vertically heterogeneous HBM-PIM architecture for KV-centric LLM serving that leverages HBM4's logic-die substrate. TokenStack separates each stack into dense capacity layers and PIM-enabled compute layers, then uses the logic base die as a stack-local control point that manages cross-layer movement without host-side overhead. The base-die controller handles cross-layer DMA, layered address translation, attention-side gather/broadcast coordination, and inline quantization during migration. On top of this hardware, TokenStack uses topology-aware KV placement, workload-aware eviction, and bounded replication to keep hot KV near PIM compute while moving colder state to dense layers. Using production-derived traces across four models, completed multi-QPS runs show that TokenStack increases geometric-mean token throughput by 1.62x and SLO-compliant serving capacity by 1.70x over AttAcc, and reduces per-token energy by 30-47%.

cs.AR↗

arXiv2026

TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing

Multi-agent LLM applications organize execution in synchronized rounds where a central scheduler gathers outputs from all agents and redistributes the combined context. This All-Gather communication pattern creates massive KV Cache redundancy, because every agent's prompt contains the same shared output blocks, yet existing reuse methods fail to exploit it efficiently. We present TokenDance, a system that scales the number of concurrent agents by exploiting the All-Gather pattern for collective KV Cache sharing. TokenDance's KV Collector performs KV Cache reuse over the full round in one collective step, so the cost of reusing a shared block is paid once regardless of agent count. Its Diff-Aware Storage encodes sibling caches as block-sparse diffs against a single master copy, achieving 11-17x compression on representative workloads. Evaluation on GenerativeAgents and AgentSociety shows that TokenDance supports up to 2.7x more concurrent agents than vLLM with prefix caching under SLO requirement, reduces per-agent KV Cache storage by up to 17.5x, and achieves up to 1.9x prefill speedup over per-request position-independent caching.

cs.DC↗

arXiv2025

TokenSim: Enabling Hardware and Software Exploration for Large Language Model Inference Systems

The increasing demand for large language model (LLM) serving has necessitated significant advancements in the optimization and profiling of LLM inference systems. As these models become integral to a wide range of applications, the need for efficient and scalable serving solutions has grown exponentially. This work introduces TokenSim, a comprehensive hardware and software exploration system designed specifically for LLM inference. TokenSim is characterized by its support for extensible system optimizations including scheduling and memory management. We validate the results with systems running with realworld datasets, achieving an error rate of less than 1%. Furthermore, TokenSim facilitates various insightful explorations into the performance and optimization of LLM serving systems.

cs.DC↗