← Back to all news
arXiv Machine Learning By Omkar Shewale, Deepak Kumar, Divakar Kumar Yadav

PrefixBench-H100: Characterizing Prefix Reuse and Time-to-First-Token in H100 LLM Serving

Read the original on arXiv Machine Learning →

PrefixBench-H100 is a reproducible benchmark that evaluates how reusing prompt prefixes affects LLM serving performance on NVIDIA H100 GPUs. It tests two popular runtimes (vLLM and TensorRT-LLM) across varied workloads, measuring metrics such as time-to-first-token, latency, throughput, cache hits, and GPU memory usage. The study identifies when prefix reuse significantly reduces first‑token latency and when cache pressure diminishes those gains, noting that cache effectiveness is largely unaffected by concurrency or output length, while differences arise mainly in scheduling.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 25

When Fancy Eviction Fails: Rethinking Cache Replacement For LLM Prefix Reuse

The paper investigates cache replacement strategies for large language model (LLM) prefix reuse, analyzing production traces from two companies and testing 14 eviction algorithms in both high-bandwidth memory (HBM) and large memory-pool environments. It finds that sophisticated policies designed for traditional caches offer little advantage over simple LRU, because prefix reuse is largely driven by the regular pacing of active sessions, making recency a strong predictor. The study also highlights new challenges such as heavy-tailed session footprints and variable miss costs, and proposes a compute-savings ratio along with two offline oracles to better quantify these effects, suggesting that effective prefix-cache management should combine recency with selective quick demotion, compute-aware partial eviction, and capacity-dependent granularity.

By Yiyu Liu, Minlan Yu, Juncheng Yang
llmsagents
More like this →
arXiv Machine Learning
Sep 29

The KV Cache Is the New Memory Wall

The paper argues that for large‑context autoregressive language‑model inference, memory bandwidth—specifically the Key‑Value (KV) cache—becomes the limiting resource rather than arithmetic throughput. It analytically derives how arithmetic intensity decays with context length for NVIDIA H100, NVIDIA B200, and AMD MI300X, identifies crossover points where KV traffic overtakes weight traffic, and evaluates representative techniques across five compression domains. The study finds a three‑regime behavior: below the crossover, weight traffic dominates and KV compression offers little benefit; beyond it, KV traffic dominates and compression methods trade quality for bandwidth, with paging and prefix sharing being lossless but capacity‑limited, while quantization and eviction directly reduce bandwidth at the cost of accuracy. whyItMatters":"The work provides a unified analytical framework and a standardized protocol that enable consistent comparison of KV‑compression techniques across hardware and workloads, guiding practitioners in selecting appropriate methods for long‑context inference."

By Tejinder Singh
llmsefficiency
More like this →
arXiv Computation and Language
Aug 27

TOPAS: Workflow-Aware Prefix-State Scheduling for Multi-Agent LLM Serving

TOPAS is a Task‑Oriented Prefix‑Aware Scheduler designed for multi‑agent large language model serving. It jointly decides which agent prefixes to retain in a shared key‑value cache and which requests to schedule, balancing the reduction of each task’s longest remaining service path against the benefit of downstream prefix reuse while accounting for movement and preemption costs. Experiments on synthetic DAGs and MetaGPT software‑development workflows show that TOPAS can reduce mean and p99 job completion times by up to 39.8%/49.4% and 22.0%/26.6% respectively compared to the best baselines.

By Hongqiu Ni, Han Tian, Chi Zhang, Guopeng Li, Haisheng Tan
llmsagentsefficiency
More like this →