Pith. sign in

REVIEW 8 cited by

MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache

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 2401.14361 v3 pith:GTP3RAT2 submitted 2024-01-25 cs.LG cs.PF

classification cs.LGcs.PF
keywords moe-infinitycacheexpertinferencemachinespersonalactivationduring
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper presents MoE-Infinity, an efficient MoE inference system designed for personal machines with limited GPU memory capacity. The key idea for MoE-Infinity is that on personal machines, which are often single-user environments, MoE-based LLMs typically operate with a batch size of one. In this setting, MoE models exhibit a high degree of activation sparsity, meaning a small number of experts are frequently reused in generating tokens during the decode phase. Leveraging this idea, we design a sparsity-aware expert cache, which can trace the sparse activation of experts during inference and carefully select the trace that represents the sparsity pattern. By analyzing these selected traces, MoE-Infinity guides the replacement and prefetching of the expert cache, providing 3.1-16.7x per-token latency improvements over numerous state-of-the-art systems, including vLLM, Ollama, DeepSpeed and BrainStorm across various MoE models (DeepSeek and Mixtral) when handling different LLM tasks. MoE-Infinity's source code is publicly available at https://github.com/EfficientMoE/MoE-Infinity

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

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

  1. Beyond Global Routing Aggregation: Phase-Aware Expert Merging for MoE Vision-Language Models

    cs.CV 2026-08 conditional novelty 7.0 of 10

    Phase-aware expert merging based on routing role profiles preserves more MoE-VLM accuracy than global routing aggregation at matched compression ratios.

  2. Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study

    cs.PF 2026-06 accept novelty 6.5 of 10

    On bandwidth-bound edge hardware, MoE inference cost tracks total parameters rather than active ones, so sparse activation fails to deliver the expected throughput or energy gains.

  3. HetRoute Heterogeneous and Cost-aware Collaborative Routing Framework for Distributed Edge MoE Inference

    cs.NI 2026-08 conditional novelty 6.0 of 10

    A routing framework for distributed edge MoE inference that co-optimizes expert placement, GPU/CPU residency, quantization precision, and per-token set-level routing, reporting large latency and throughput gains in si...

  4. DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Fixed-footprint shared+top-1+draft-expert self-speculation with residual/router distillation, expansion-aware truncation, and prefetch raises end-device MoE decode throughput ~1.45× while keeping exact target outputs.

  5. Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices

    cs.DC 2026-07 conditional novelty 6.0 of 10

    Tensor-granularity hybrid CPU-GPU offloading with static placement plus load-aware dynamic transfer yields up to 1.94× prefill and 3.29× decode throughput for local LLMs on consumer devices.

  6. Accelerating Mixture-of-Expert Inference with Adaptive Expert Split Mechanism

    cs.LG 2025-09 conditional novelty 6.0 of 10

    MoEpic splits each MoE expert into a cached top segment and a prefetched bottom segment, raising cache hit rates and hiding loading latency to accelerate offloaded MoE inference.

  7. MoE-Compression: How the Compression Error of Experts Affects the Inference Accuracy of MoE Model?

    cs.LG 2025-09 reject novelty 5.0 of 10

    In a 26-layer MoE model, injecting Gaussian weight errors into middle-layer experts hurts math accuracy most, while deep-layer errors can sometimes improve instruction compliance.

  8. MoE-Beyond: Learning-Based Expert Activation Prediction on Edge Devices

    cs.LG 2025-08 unverdicted novelty 4.0 of 10

    An abstract-only MoE paper claiming 97.5% activation prediction accuracy and a 17% to 72% cache hit rate gain, whose full text is a different paper on functional equations, making the results unverifiable.

Pith tools