TheMachine Press

A daily newspaper for the age of artificial intelligence.

Morning editionPermanent story

chips infrastructure

The Fleet Stopped Profiling When the Decision Stopped Moving

FleetSieve measures only the LLM-serving configurations likely to change a resource-coupled allocation.

Published Updated Story ID: mp-2026-08-23-004
Read the complete editionStory JSON

Summary

FleetSieve measures only the LLM-serving configurations likely to change a resource-coupled allocation.

On a fixed H100 grid for a 31-billion-parameter open model, the method matched the oracle aggregate choice with 6.9 percent fewer GPU-seconds than uniform random profiling in the fixed comparison. Its joint capacity and tail-latency model also avoided a configuration whose 46.4-second p99 violated a 30-second service objective, although the paper reports that FleetSieve did not use the fewest GPU-seconds for every workload.

Why it matters

FleetSieve measures only the LLM-serving configurations likely to change a resource-coupled allocation.

Limits and context

  • Its joint capacity and tail-latency model also avoided a configuration whose 46.4-second p99 violated a 30-second service objective, although the paper reports that FleetSieve did not use the fewest GPU-seconds for every workload.

Key claims

  1. FleetSieve measures only the LLM-serving configurations likely to change a resource-coupled allocation.

    Qualification: Its joint capacity and tail-latency model also avoided a configuration whose 46.4-second p99 violated a 30-second service objective, although the paper reports that FleetSieve did not use the fewest GPU-seconds for every workload.

    Evidence: source-2026-08-23-004

Sources

  1. arXiv preprint 2608.19659arXiv · primary research

Corrections

No corrections have been recorded for this story.