cd /news/large-language-models/rethinking-bursty-workloads-and-kv-c… · home topics large-language-models article
[ARTICLE · art-82578] src=systems.seas.harvard.edu ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Rethinking Bursty Workloads and KV Cache Hierarchies for Efficient LLM Serving

Akira van de Groenendaal, a senior studying Computer Science at Carnegie Mellon University, presented research at the Harvard Systems Group showing that bursty workloads can improve the time-per-output-token of LLM clusters and that controlling the private vs shared split of a distributed KV cache can optimize time-to-first-token, challenging conventional systems choices in LLM serving.

read1 min views1 publishedJul 31, 2026

Abstract #

Modern LLM inference workloads are bursty and exhibit heavy prefix reuse, and serving them efficiently requires understanding how we can turn these traits to our advantage. In this talk, I’ll present two recent projects: the first investigates how latency is impacted by bursty arrivals, and the second explores how we can make best use of a distributed KV cache. First, we’ll see how burstiness can improve the time-per-output-token of your LLM cluster and discuss the conditions which make this possible, as well as what it implies for request routing. Afterwards, we’ll look at how to control the private vs shared split of your KV cache to optimize time-to-first-token. Both projects show how intuitive systems choices can sometimes leave performance gains on the table, motivating the need to question seemingly obvious decisions.

Bio #

Akira van de Groenendaal is a senior studying Computer Science at Carnegie Mellon University, currently doing research with the Harvard Systems Group under Prof. Juncheng Yang. He works on ML systems, with interests in workload analysis and the queueing dynamics of LLM inference.

── more in #large-language-models 4 stories · sorted by recency
── more on @akira van de groenendaal 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/rethinking-bursty-wo…] indexed:0 read:1min 2026-07-31 ·