mlsanityData to 14 Oct 2026

XShare: Collaborative in-Batch Expert Sharing for Faster MoE Inference

arXiv 2602.07265 ↗First posted 6 Feb 2026cs.LG cs.AIcited by 7

On the map: Mixture-of-experts → Efficient MoE training and inference systems

also in 1 more
Abstract (arXiv)

Mixture-of-Experts (MoE) architectures are increasingly used to efficiently scale large language models. However, in production inference, request batching and speculative decoding significantly amplify expert activation, eroding these efficiency benefits. We address this issue by modeling batch-aware expert selection as a modular optimization problem and designing efficient greedy algorithms for different deployment settings. The proposed method, namely XShare, requires no retraining and dynamically adapts to each batch by maximizing the total gating score of selected experts. It reduces expert activation by up to 30% under standard batching, cuts peak GPU load by up to 3x in expert-parallel deployments, and achieves up to 14% throughput gains in speculative decoding via hierarchical, correlation-aware expert selection even if requests in a batch drawn from heterogeneous datasets.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Efficient MoE training and inference systems, one of 12 directions in Mixture-of-experts. Builds on 17 of its 22 references that are in the map. First posted on arXiv 6 Feb 2026.

Builds on

17 of 22 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Lynx: Enabling Efficient MoE Inference through Dynamic Batch-Aware Expert Selection13 Nov

Other references · 16

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  2. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  3. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  4. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  5. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  6. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,631
  7. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,228
  8. 2025EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Testcited by 331
  9. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 227
  10. 2024Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Modelscited by 146
  11. 2024MoE-Pruner: Pruning Mixture-of-Experts Large Language Model using the Hints from Its Routercited by 62
  12. 2024Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costscited by 53
4 more
  1. 2025Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Modelscited by 50
  2. 2025DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruningcited by 26
  3. 2025Beyond Benchmarks: Understanding Mixture-of-Experts Models through Internal Mechanismscited by 7
  4. 2025Opportunistic Expert Activation: Batch-Aware Expert Routing for Faster Decode Without Retrainingcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 7.

7 papers.

  1. 2026ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Servingcited by 3
  2. 2026Layer-wise MoE Routing Locality under Shared-Prefix Code Generation: Token-Identity Decomposition and Compile-Equivalent Fork Redundancycited by 1
  3. 2026AcceptMoE: Commitment-Weighted Self-Sizing Verifier Expert Sets for Efficient MoE Speculative Decodingcited by 1
  4. 2026Think Before You Grid-Search: Floor-First Triage for LLM Servingcited by 0
  5. 2026PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Compositioncited by 0
  6. 2026ACE: Adaptive Calibration-Free Expert Skipping for MoE-based LLMscited by 0
  7. 2026SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Servingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Fast MoE Inference via Predictive Prefetching and Expert Replication
  2. 2026Speculating Experts Accelerates Inference for Mixture-of-Experts
  3. 2026BASE: Batch-Aware Selection of Experts Using Predicted Removal Error for Efficient MoE Decoding
  4. 2025Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline
  5. 2025Accelerating Mixture-of-Expert Inference with Adaptive Expert Split Mechanism
  6. 2025OD-MoE: On-Demand Expert Loading for Cacheless Edge-Distributed MoE Inference
  7. 2026Dynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMs
  8. 2024HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference