Pith. sign in

REVIEW 1 cited by

Is the GPU Half-Empty or Half-Full? Practical Scheduling Techniques for LLMs

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.17840 v2 pith:IRIDTZ3V submitted 2024-10-23 cs.LG

Is the GPU Half-Empty or Half-Full? Practical Scheduling Techniques for LLMs

classification cs.LG
keywords schedulingpracticaltechniqueseasyimplementoftenrequestsserving
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Serving systems for Large Language Models (LLMs) improve throughput by processing several requests concurrently. However, multiplexing hardware resources between concurrent requests involves non-trivial scheduling decisions. Practical serving systems typically implement these decisions at two levels: First, a load balancer routes requests to different servers which each hold a replica of the LLM. Then, on each server, an engine-level scheduler decides when to run a request, or when to queue or preempt it. Improved scheduling policies may benefit a wide range of LLM deployments and can often be implemented as "drop-in replacements" to a system's current policy. In this work, we survey scheduling techniques from the literature and from practical serving systems. We find that schedulers from the literature often achieve good performance but introduce significant complexity. In contrast, schedulers in practical deployments often leave easy performance gains on the table but are easy to implement, deploy and configure. This finding motivates us to introduce two new scheduling techniques, which are both easy to implement, and outperform current techniques on production workload traces.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Auto-Scaling Heterogeneous Neural Processing Units for Energy and Cost-Efficient LLM Serving

    cs.AR 2026-07 conditional novelty 6.0

    NeuScale routes LLM inference requests to the most energy/cost-efficient configuration of heterogeneous NPU chips using roofline allocation and runtime auto-scaling.