# PROBE: Co-Balancing Computation and Communication in MoE Inference via Real-Time Predictive Prefetching

arXiv: https://arxiv.org/abs/2602.00509 · HTML: https://mlsanity.com/paper/2602.00509/

## Key facts

- Cited by 4 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 24 of its 48 references that are in the map.
- First posted on arXiv 31 Jan 2026.

## Placed in

- Mixture-of-experts / [Efficient MoE training and inference systems](https://mlsanity.com/moe/efficient-moe-training-and-inference-systems/)

## Builds on (most cited first, 24 of 24)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models](https://mlsanity.com/paper/2401.06066/) (2024)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Instruction Tuning with GPT-4](https://mlsanity.com/paper/2304.03277/) (2023)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test](https://mlsanity.com/paper/2503.01840/) (2025)
- [Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts](https://mlsanity.com/paper/2408.15664/) (2024)
- [OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models](https://mlsanity.com/paper/2402.01739/) (2024)
- [Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding](https://mlsanity.com/paper/2507.19427/) (2025)
- [Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models](https://mlsanity.com/paper/2501.11873/) (2025)
- [Advancing Expert Specialization for Better MoE](https://mlsanity.com/paper/2505.22323/) (2025)
- [MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism](https://mlsanity.com/paper/2504.02263/) (2025)
- [SonicMoE: Accelerating MoE with IO and Tile-aware Optimizations](https://mlsanity.com/paper/2512.14080/) (2025)
- [BlendServe: Optimizing Offline Inference for Auto-regressive Large Models with Resource-aware Batching](https://mlsanity.com/paper/2411.16102/) (2024)
- [GRACE-MoE: Grouping and Replication with Locality-Aware Routing for Efficient Distributed MoE Inference](https://mlsanity.com/paper/2509.25041/) (2025)
- [Semantic Parallelism: Redefining Efficient MoE Inference via Model-Data Co-Scheduling](https://mlsanity.com/paper/2503.04398/) (2025)
- [HarMoEny: Efficient Multi-GPU Inference of MoE Models](https://mlsanity.com/paper/2506.12417/) (2025)
- [Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design](https://mlsanity.com/paper/2504.01337/) (2025)

## Built on by (most cited first, 4 of 4)

- [UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing](https://mlsanity.com/paper/2606.04101/) (2026)
- [OrderMoE: An expert similarity driven distributed edge MoE inference](https://mlsanity.com/paper/2607.17154/) (2026)
- [HCRMap: Pressure-Aware Hot-Expert Residency Mapping for 3.5D MoE Chiplet Inference](https://mlsanity.com/paper/2607.11586/) (2026)
- [TrimMoE A communication aware and adaptive depth framework for distributed edge inference](https://mlsanity.com/paper/2608.00573/) (2026)

## Abstract (arXiv)

Mixture-of-Experts models have become a dominant architecture for scaling Large Language Models by activating only a sparse subset of experts per token. However, latency-critical MoE inference faces a fundamental tension: while expert parallelism improves memory efficiency, it also amplifies execution stragglers. In real-world serving, continuous batching and diverse concurrent requests induce rapid semantic shifts, causing expert hotspots to migrate abruptly across GPUs and triggering the 'double penalty' of coupled computational skew and network congestion. We propose PROBE, an inference system that co-balances computation and communication in real time. PROBE introduces Continuous Lookahead Pipelining, which proactively predicts, plans, and prefetches for upcoming layers while keeping all control overheads off the critical path. PROBE consists of: (1) a Gate-Initialized Lookahead Predictor that distills the target router to forecast next-layer expert activation with high fidelity; (2) a Hardware-Aware Balance Planning solver that jointly optimizes dynamic expert replication and token assignment under strict hiding-window constraints; and (3) a Phase-Locked Co-Scheduling policy that uses split-phase transmission to hide bandwidth-intensive expert transfers behind computation without contending with All-to-All collectives. Experiments show that PROBE reduces prefill latency by up to 1.32X and improves decoding throughput by up to 1.26X over state-of-the-art baselines, especially under extreme workload volatility.