Papers › Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline

Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline

9 Feb 2025arXiv:2502.06888archive 2025-07-28

Zhiyuan Fang, Yuegui Huang, Zicong Hong, Yufeng Lyu, Wuhui Chen, Yue Yu, Fan Yu, Zibin Zheng

Mixture of Experts (MoE), with its distinctive sparse structure, enables the scaling of language models up to trillions of parameters without significantly increasing computational costs. However, the substantial parameter size presents a challenge for inference, as the expansion in GPU memory cannot keep pace with the growth in parameters. Although offloading techniques utilise memory from the CPU and disk and parallelise the I/O and computation for efficiency, the computation for each expert in MoE models is often less than the I/O, resulting in numerous bubbles in the pipeline. Therefore, we propose Klotski, an efficient MoE inference engine that significantly reduces pipeline bubbles through a novel expert-aware multi-batch pipeline paradigm. The proposed paradigm uses batch processing to extend the computation time of the current layer to overlap with the loading time of the next layer. Although this idea has been effectively applied to dense models, more batches may activate more experts in the MoE, leading to longer loading times and more bubbles. Thus, unlike traditional approaches, we balance computation and I/O time and minimise bubbles by orchestrating their inference orders based on their heterogeneous computation and I/O requirements and activation patterns under different batch numbers. Moreover, to adapt to different hardware environments and models, we design a constraint-sensitive I/O-compute planner and a correlation-aware expert prefetcher for a schedule that minimises pipeline bubbles. Experimental results demonstrate that Klotski achieves a superior throughput-latency trade-off compared to state-of-the-art techniques, with throughput improvements of up to 85.12x.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

MindSpore-scientific-2/code-7 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to High-Performance Temporal Reversible Spiking Neural Networks with O(L) Training Memory... (arXiv:2405.16466; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 1 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Mixture-of-Experts

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

MoE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections