🛰️ Daily AI Frontier
‹ back to 2026-08-09

LLM Inference Under Bursty Workload Distribution: Modifying the WAIT Algorithm

Research Efficiency & Systems

Ranking

Overall 58
Content 65
Popularity 42

Observed public metrics from 1 member.

Representative image for LLM Inference Under Bursty Workload Distribution: Modifying the WAIT Algorithm

Merged summary

TL;DR - An arXiv preprint extending the WAIT LLM-serving scheduler to handle bursty, time-varying request traffic instead of the usual constant-rate Poisson assumption. It matters because real inference workloads are dynamic, and scheduling tuned for a fixed arrival rate leaves throughput on the table.

  • Argues prior LLM scheduling work assumes stationary Poisson arrivals, which misrepresents real-world bursty traffic patterns.
  • Adds a lightweight extension to the state-of-the-art WAIT algorithm that performs online estimation of request intensity from observed interarrival times, requiring no prior traffic knowledge.
  • Evaluated in simulation using Markov Modulated Poisson Process (MMPP) synthetic workloads with diverse request types.
  • Reports higher throughput than Sarathi-Serve, ORCA, and vLLM in the evaluated low arrival-rate shift scenarios, with comparable latency; results are simulation-only, not measured on a real serving stack.

Sources (1)

LLM Inference Under Bursty Workload Distribution: Modifying the WAIT Algorithm

arXiv cs.LG Anjali Gangadhar Katageria, Shobha Rani, Raghu Nandan Sengupta 2026-08-06 arXiv:2608.06135
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-08-21 14:24:44.370435 UTC

TL;DR - An arXiv preprint extending the WAIT LLM-serving scheduler to handle bursty, time-varying request traffic instead of the usual constant-rate Poisson assumption. It matters because real inference workloads are dynamic, and scheduling tuned for a fixed arrival rate leaves throughput on the table.

  • Argues prior LLM scheduling work assumes stationary Poisson arrivals, which misrepresents real-world bursty traffic patterns.
  • Adds a lightweight extension to the state-of-the-art WAIT algorithm that performs online estimation of request intensity from observed interarrival times, requiring no prior traffic knowledge.
  • Evaluated in simulation using Markov Modulated Poisson Process (MMPP) synthetic workloads with diverse request types.
  • Reports higher throughput than Sarathi-Serve, ORCA, and vLLM in the evaluated low arrival-rate shift scenarios, with comparable latency; results are simulation-only, not measured on a real serving stack.
item →