跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.24891 · v1

Cap-and-Track: Optimizing LLM Inference Request Dispatch Across Shifting Capacity

首次提交 2026-11-19 02:34
版本更新 2026-11-19 02:34
雷达观测 2026-11-19 15:04
arXiv ↗PDF ↗

摘要

A fixed dispatch rate for LLM inference becomes stale as serving fleets resize and request sizes change. Generative output length is unknown at admission, and shared provider pools can lose capacity. We present Cap-and-Track, a design for asynchronous inference across provider capacity and internal GPUs. Meta's traffic shaper implements Cap-and-Track for post and live-video understanding. Refusals signal the backend's current admission ceiling. Durable priority queues hold excess work outside execution, including refused requests for retry. Cap is a fail-fast admission check at the saturated resource that refuses work before a long wait. Using only those refusals, the Track dispatcher probes upward and backs off. It follows the ceiling without output-length prediction or a fleet-level rate to retune. In a concurrent same-traffic production A/B, the shaper ran per-replica Cap plus Track. It served a classifier on 43% fewer H100s than its queued, fixed-rate precursor, though lower-priority work waited longer at backfill peaks. In steady-capacity real-engine replay, Track ran within 1% of the goodput of a fixed rate tuned above measured capacity, with about a quarter of that rate's refusal share. The shaper carries more than 300 million online requests and hundreds of terabytes of media a day. During a backfill, it handled 1.1 billion requests in its busiest 24 hours. Lessons include keeping queues inside inference engines just long enough to fill batches, steering dispatch by capacity refusals alone, keeping dispatch stateful, and sizing fleets by how long low-priority work can wait.

作者备注:20 pages, 6 figures, 2 tables. Includes appendices

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 · 2026-11-19 02:34 · 最新观测版本

Cap-and-Track: Optimizing LLM Inference Request Dispatch Across Shifting Capacity

A fixed dispatch rate for LLM inference becomes stale as serving fleets resize and request sizes change. Generative output length is unknown at admission, and shared provider pools can lose capacity. We present Cap-and-Track, a design for asynchronous inference across provider capacity and internal GPUs. Meta's traffic shaper implements Cap-and-Track for post and live-video understanding. Refusals signal the backend's current admission ceiling. Durable priority queues hold excess work outside execution, including refused requests for retry. Cap is a fail-fast admission check at the saturated resource that refuses work before a long wait. Using only those refusals, the Track dispatcher probes upward and backs off. It follows the ceiling without output-length prediction or a fleet-level rate to retune. In a concurrent same-traffic production A/B, the shaper ran per-replica Cap plus Track. It served a classifier on 43% fewer H100s than its queued, fixed-rate precursor, though lower-priority work waited longer at backfill peaks. In steady-capacity real-engine replay, Track ran within 1% of the goodput of a fixed rate tuned above measured capacity, with about a quarter of that rate's refusal share. The shaper carries more than 300 million online requests and hundreds of terabytes of media a day. During a backfill, it handled 1.1 billion requests in its busiest 24 hours. Lessons include keeping queues inside inference engines just long enough to fill batches, steering dispatch by capacity refusals alone, keeping dispatch stateful, and sizing fleets by how long low-priority work can wait.

查看此版本解读 →查看此版本原文 ↗