# SPICE: Speculative Prefetching with Low-Rank Expert Surrogates and Heterogeneous Orchestration for MoE Inference Acceleration

arXiv: https://arxiv.org/abs/2608.21240 · HTML: https://mlsanity.com/paper/2608.21240/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Efficient MoE training and inference systems, one of 12 directions in Mixture-of-experts.
- Builds on 1 of its 18 references that are in the map.
- First posted on arXiv 21 Aug 2026.

## Placed in

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

## Builds on (most cited first, 1 of 1)

- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)

## Abstract (arXiv)

Mixture-of-Experts (MoE) models are increasingly used in LLMs because sparse activation decouples model capacity from compute cost. However, the large expert parameter footprint often exceeds GPU memory capacity, making inference latency dominated by the host-to-device PCIe transfers for expert loading. To address these challenges, this paper presents SPICE, a speculative prefetching framework for MoE offloading that combines lightweight expert prediction with confidence-aware CPU-GPU orchestration. On one hand, SPICE builds a lightweight draft model aligned with the target MoE architecture, using a confidence-aware adaptive lookahead algorithm to prefetch high-confidence experts. On the other hand, when speculative predictions miss, SPICE switches to a cost-aware CPU-GPU heterogeneous orchestration: low-confidence misses are approximated by the resident shared expert with low rank expert (LoRE) surrogates, while exact residual work is offloaded to the CPU and executed asynchronously in parallel with ongoing GPU computation. Evaluated on DeepSeek-V2-Lite and Qwen2-57B-A14B across diverse GPU platforms, SPICE achieves up to 3.12 speedup in Time Per Output Token (TPOT) with minimal quality loss, showing that effective MoE offloading requires not only predicting future experts, but also deciding which misses deserve approximation, which require exact recovery, and where exact residual work should execute.