Tideway: Phase-Aware Tiered Memory Management for MoE Inference on Consumer Devices
Tideway: Phase-Aware Tiered Memory Management for MoE Inference on Consumer Devices

Tideway significantly improves the inference efficiency of large expert models (MoE) on consumer devices by treating host memory and GPU GPU memory as a unified memory pool and adopting stage-aware memory layout and CUDA graph optimization under expert paging. On typical consumer hardware, Tideway accelerates end-to-end latency by 1.97x, first token generation time by 2.40x, and decoding throughput by 1.61x. Its source code is open-sourced.
Abstract
TIDEWAY enables efficient inference of large Mixture-of-Experts models on memory-constrained consumer devices by treating host RAM and GPU VRAM as a unified memory pool with phase-aware layouts and optimized CUDA Graph execution under expert paging.
Large language model (LLM) agents are rapidly becoming a dominant paradigm for AI applications. Recently, there is a growing demand to deploy large-scale Mixture-of-Experts (MoE) models locally on consumer PCs to balance data privacy, API costs, and inference efficiency. However, unlike datacenter servers with abundant DRAM, consumer devices are tightly constrained in both GPU VRAM and host RAM, forcing massive MoE weights to spill across VRAM, host RAM, and SSD. Under such spilling, we observe that existing systems fail to fully utilize this memory hierarchy, treating the tiers as independent caches and thrashing in inference. We present TIDEWAY, a system for efficient inference of large MoE models on memory-constrained consumer devices. Our core insight is to manage host RAM and GPU VRAM as a unified memory pool. Within this pool, TIDEWAY couples phase-aware memory layouts, which adapt to the distinct access patterns of prefill and decode, with an execution engine that optimizes CUDA Graph execution under expert paging. Our evaluations on representative consumer hardware with frontier MoE models demonstrate that TIDEWAY significantly outperforms state-of-the-art systems. On average, TIDEWAY achieves speedups of 1.97x in end-to-end latency and 2.40x in Time-to-First-Token (TTFT), along with 1.61x higher decode throughput against the fastest baseline. Our source code is publicly available at https://github.com/Afterglow231/Tideway .
View arXiv page View PDF GitHub 4 Add to collection
Get this paper in your agent:
hf papers read 2611.14848
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.14848 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.14848 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.14848 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
Source: Hugging Face Daily Papers · huggingface.co