# WiSP: A Working-Set View of Mixture-of-Experts Serving on Extremely Low-Resource Hardware

arXiv: https://arxiv.org/abs/2606.21868 · HTML: https://mlsanity.com/paper/2606.21868/

## Key facts

- Cited by 2 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 32 references that are in the map.
- First posted on arXiv 20 Jun 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, 24 of 24)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding](https://mlsanity.com/paper/2412.10302/) (2024)
- [Jamba: A Hybrid Transformer-Mamba Language Model](https://mlsanity.com/paper/2403.19887/) (2024)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [Aria: An Open Multimodal Native Mixture-of-Experts Model](https://mlsanity.com/paper/2410.05993/) (2024)
- [Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference](https://mlsanity.com/paper/2308.12066/) (2023)
- [Fast Inference of Mixture-of-Experts Language Models with Offloading](https://mlsanity.com/paper/2312.17238/) (2023)
- [MoE-Lightning: High-Throughput MoE Inference on Memory-constrained GPUs](https://mlsanity.com/paper/2411.11217/) (2024)
- [Scaling Diffusion Transformers to 16 Billion Parameters](https://mlsanity.com/paper/2407.11633/) (2024)
- [LLaDA-MoE: A Sparse MoE Diffusion Language Model](https://mlsanity.com/paper/2509.24389/) (2025)
- [MoE-Infinity: Efficient MoE Inference on Personal Machines with Sparsity-Aware Expert Cache](https://mlsanity.com/paper/2401.14361/) (2024)
- [SiDA-MoE: Sparsity-Inspired Data-Aware Serving for Efficient and Scalable Large Mixture-of-Experts Models](https://mlsanity.com/paper/2310.18859/) (2023)
- [BlackMamba: Mixture of Experts for State-Space Models](https://mlsanity.com/paper/2402.01771/) (2024)
- [Taming Latency-Memory Trade-Off in MoE-Based LLM Serving via Fine-Grained Expert Offloading](https://mlsanity.com/paper/2502.05370/) (2025)
- [HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference](https://mlsanity.com/paper/2504.05897/) (2025)
- [DyMoE: Dynamic Expert Orchestration with Mixed-Precision Quantization for Efficient MoE Inference on Edge](https://mlsanity.com/paper/2603.19172/) (2026)

## Built on by (most cited first, 2 of 2)

- [AnyJev Technical Report](https://mlsanity.com/paper/2610.00831/) (2026)
- [Route-Block Membership Selects Packed-AWQ Arithmetic: A Controlled Single-Fixture Mechanism Study](https://mlsanity.com/paper/2607.26316/) (2026)

## Abstract (arXiv)

Modern local and agentic workloads often need large-model capacity at low concurrency, but run on GPUs that cannot keep a frontier-scale model resident. Mixture-of-Experts (MoE) models are a natural fit because they activate only a small subset of experts per token, but their sparsity saves computation, not residency: the full expert pool still has to be stored, and any expert used by a layer must be in GPU memory when that layer runs. Static layer-level CPU offload makes such models fit, but transfers the expert layer in bulk on every forward pass, losing much of the sparsity advantage. We view low-resource MoE serving as a working-set problem on the GPU. Routed expert weights and the KV cache are two memory-demand streams competing for the same limited VRAM. We implement this view in WiSP (Working-Set Paging), a routing-aware expert pager that plugs into an unmodified serving engine and preserves byte-identical outputs. On a real 24 GiB RTX 3090, WiSP achieves up to 2.0x the decode throughput of static offload at the same memory budget when the model does not fit. A natural next step is to predict future experts and prefetch them. We find that this does not help in single-stream decode: the bottleneck is PCIe bandwidth, not prediction quality, so speculative transfers compete with demand transfers instead of hiding them. This shifts the design question from prefetching to allocation: how should one VRAM budget be divided between resident experts and the KV cache? We answer with MV-WSA (Marginal-Value Working-Set Allocation), which splits memory by marginal latency benefit per byte while enforcing a KV-admission floor. As a startup configurator, MV-WSA is the only policy we test that stays near-best on both prefill and decode; as a live controller, it resizes both pools while serving and reduces end-to-end time by up to 1.19x over a fixed offline split, without changing model outputs.