Pith. sign in

REVIEW 2 cited by

Scattered Mixture-of-Experts Implementation

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 2403.08245 v2 pith:EKT4SQPV submitted 2024-03-13 cs.LG cs.DC

classification cs.LGcs.DC
keywords implementationmixture-of-expertsenablesfootprintmemoryparallellinearscattermoespeed
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present ScatterMoE, an implementation of Sparse Mixture-of-Experts (SMoE) on GPUs. ScatterMoE builds upon existing implementations, and overcoming some of the limitations to improve inference and training speed, and memory footprint. This implementation achieves this by avoiding padding and making excessive copies of the input. We introduce ParallelLinear, the main component we use to build our implementation and the various kernels used to speed up the operation. We benchmark our implementation against Megablocks, and show that it enables a higher throughput and lower memory footprint. We also show how ParallelLinear enables extension of the Mixture-of-Experts concept by demonstrating with an implementation of Mixture of Attention.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Cross-Platform Fused MoE Dispatch in Triton: Portable Expert Routing Without CUDA

    cs.DC 2026-04 conditional novelty 5.5 of 10

    A pure-Triton fused MoE dispatch kernel reaches 89–131% of CUDA Megablocks throughput at inference batch sizes and passes all tests on both NVIDIA A100 and AMD MI300X with zero code changes.

  2. Scaling Fine-Grained MoE Beyond 50B Parameters: Empirical Evaluation and Practical Insights

    cs.LG 2025-06 conditional novelty 5.0 of 10

    At 56B total parameters, fine-grained MoE with smaller, more numerous experts beats standard Switch and Mixtral-style MoE on validation loss and average downstream accuracy at matched FLOPs.

Pith tools