跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.22746 · v1

LaFlash: Capacity-Driven Acceleration for Coding Agent Workflows via QLC-HBF

首次提交 2026-11-17 21:16
版本更新 2026-11-17 21:16
雷达观测 2026-11-18 19:41
arXiv ↗PDF ↗

摘要

As large language models (LLMs) evolve toward agentic AI, coding agents are emerging as memory-intensive workloads that repeatedly reuse persistent states, including contexts and KV caches. Emerging agentic workflows, including Loop/Graph Engineering, cause state amplification through frequent active/dormant transitions, increasing memory pressure. Evicted states incur costly recomputation upon reactivation, particularly under long-context, short-decode workloads. This motivates Capacity-Driven Acceleration (CDA), which explicitly accounts for state amplification to allocate memory capacity between active concurrency and dormant-state retention, replacing recomputation with memory access. In this work, we propose LaFlash, a High-Bandwidth Flash (HBF) architecture that exploits the large capacity of Quad-Level Cell (QLC)-based flash to realize CDA. However, QLC's long read latency demands massive read parallelism under irregular state reactivation and varying context lengths, while limited write endurance constrains placement. LaFlash introduces Session Grouping to balance active request counts and aggregate context lengths across groups, sustaining read parallelism and block utilization through request-exclusive allocation. Furthermore, Fast-Page Allocation exploits QLC's read-latency heterogeneity to mitigate residual inter-group imbalance and sustain bandwidth utilization. On end-to-end coding agent workloads, LaFlash achieves 7.04×\times higher throughput and 10.96×\times higher energy efficiency over SLC-HBF with batch expansion, and 2.36×\times higher throughput over QLC-HBF with CDA. HBM buffering further reduces unnecessary NAND writes, improving QLC write endurance. These results demonstrate the benefits of jointly optimizing state retention and physical data placement for capacity-driven acceleration.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-17 21:16 · 最新观测版本

LaFlash: Capacity-Driven Acceleration for Coding Agent Workflows via QLC-HBF

As large language models (LLMs) evolve toward agentic AI, coding agents are emerging as memory-intensive workloads that repeatedly reuse persistent states, including contexts and KV caches. Emerging agentic workflows, including Loop/Graph Engineering, cause state amplification through frequent active/dormant transitions, increasing memory pressure. Evicted states incur costly recomputation upon reactivation, particularly under long-context, short-decode workloads. This motivates Capacity-Driven Acceleration (CDA), which explicitly accounts for state amplification to allocate memory capacity between active concurrency and dormant-state retention, replacing recomputation with memory access. In this work, we propose LaFlash, a High-Bandwidth Flash (HBF) architecture that exploits the large capacity of Quad-Level Cell (QLC)-based flash to realize CDA. However, QLC's long read latency demands massive read parallelism under irregular state reactivation and varying context lengths, while limited write endurance constrains placement. LaFlash introduces Session Grouping to balance active request counts and aggregate context lengths across groups, sustaining read parallelism and block utilization through request-exclusive allocation. Furthermore, Fast-Page Allocation exploits QLC's read-latency heterogeneity to mitigate residual inter-group imbalance and sustain bandwidth utilization. On end-to-end coding agent workloads, LaFlash achieves 7.04×\times higher throughput and 10.96×\times higher energy efficiency over SLC-HBF with batch expansion, and 2.36×\times higher throughput over QLC-HBF with CDA. HBM buffering further reduces unnecessary NAND writes, improving QLC write endurance. These results demonstrate the benefits of jointly optimizing state retention and physical data placement for capacity-driven acceleration.

查看此版本解读 →查看此版本原文 ↗