The paper investigates whether training Mixture-of-Experts (MoE) routers can improve memory‑bandwidth locality on consumer GPUs. Using a new zero‑surgery telemetry tool, the authors measure that a large Qwen3‑235B model is bottlenecked by disk‑based expert access, and that an LRU cache can serve a majority of requests. They pre‑register experiments training 137 M‑parameter MoE models with locality‑aware losses, finding that while cache misses can drop up to 60 % (99 % static‑pin hit rate), every configuration fails to meet a strict 1 % perplexity threshold, indicating a tight coupling between cache efficiency and model quality.
By Shriniwas Ramesh Suram
arXiv:2609.14507v1 Announce Type: cross
Abstract: Single-GPU long-context inference with Mixture-of-Experts (MoE) models requires spilling the key-value cache (KVCache) to CPU memory. The spilled KV...
By Enda Yu, Dezun Dong, Xiangke Liao
Serving a 235B-parameter Mixture-of-Experts (MoE) model on a single 8 GB GPU is bottlenecked not by compute but by memory bandwidth: decode must stream each token's active experts from whichever tier holds them, and on consumer hardware most experts sit on an SSD far slower than RAM. We quantify this bandwidth wall on Qwen3-235B (Q4_K_M, 134 GB): measured decode is 0.
WiSP (Working‑Set Paging) is a routing‑aware expert pager that allows Mixture‑of‑Experts models to run on GPUs that cannot hold the entire expert pool by paging experts in and out of VRAM while preserving byte‑identical outputs. On a 24 GiB RTX 3090, WiSP doubles decode throughput compared to static offload when the model does not fit, and its companion policy MV‑WSA allocates VRAM between resident experts and KV cache based on marginal latency benefit, reducing end‑to‑end time by up to 1.19× without altering model outputs.
By Jiamu Zhang, Liang Wu, Mayank Darbari, Liangjie Hong
arXiv:2606. 21633v2 Announce Type: replace Abstract: The KV cache dominates GPU memory in long-context LLM serving, crowding out batch capacity and leaving GPU compute idle.
By Omin Kwon, Doyeon Kim, Jongseok Park, Seung Yul Lee, Ion Stoica, Jae W. Lee
arXiv:2607. 14568v1 Announce Type: cross Abstract: A companion study ran a 35B mixture-of-experts model on a 2011 NVIDIA Tesla C2075 (Fermi, sm_20, 6GB) as a GPU-prefill/CPU-decode hybrid, because the 4-bit model did not fit in device memory (arXiv:2606.
By A. C. Opus, J. Q. Lu
arXiv:2608.21719v1 Announce Type: cross
Abstract: AI inference clusters are increasingly constrained by instantaneous power, not just energy: grid operators condition new capacity on demand response,...
By Yueying Li, Jiayang Chen, Yuanfan Chen, Leo Han, Haoran Qiu, Esha Choukse, Rodrigo Fonseca, Udit Gupta
Dynamic Expert Quantization (DynaExq) is a runtime-aware mixed-precision serving system designed for single‑GPU Mixture‑of‑Experts (MoE) inference under a hard high‑bandwidth memory (HBM) envelope. It treats the problem as an online, budget‑constrained precision allocation task, keeping the most frequently used experts at higher precision while relegating the rest to low‑precision fallbacks. By estimating expert hotness from router traces and asynchronously promoting or demoting experts, DynaExq maintains a fully materialized expert set during the forward pass, improving accuracy and throughput compared to static post‑training quantization and offloading/prefetch baselines.
whyItMatters":"DynaExq enables efficient deployment of large MoE models on memory‑limited GPUs by dynamically allocating precision based on runtime expert usage, thereby reducing memory footprint and latency while boosting accuracy and throughput."
By Kexin Chu, Dawei Xiang, Zixu Shen, Yiwei Yang, Zecheng Liu, Wei Zhang
arXiv:2608.28044v1 Announce Type: cross
Abstract: Large language model (LLM) inference serving is priced by tokens, but GPU energy is consumed over inference windows. This accounting mismatch makes t...
By Prabhu Vellaisamy, Vanessa Lam, Shawn Blanton, John Paul Shen
arXiv:2607. 22785v1 Announce Type: cross Abstract: Apple-Silicon SoCs share CPU, GPU, and Neural Engine over one unified memory system, raising the question of whether transformer inference can be accelerated by splitting single operators across units.
By Om Mohite
arXiv:2606. 01502v1 Announce Type: cross Abstract: Frontier LLMs increasingly decide what a query attends to with a sparse-attention indexer that picks a few KV-cache blocks per query: attention's unit is now a small, reusable chunk.
By Bole Ma, Jan Eitzinger, Harald K\"ostler, Gerhard Wellein
FluxMoE introduces an expert paging system that decouples Mixture-of-Experts (MoE) model experts from permanent GPU residency, allowing dynamic adaptation to available memory. By combining PagedTensor, a bandwidth‑balanced memory hierarchy, and a budget‑aware residency planner, FluxMoE streams expert weights on demand while keeping computations on GPUs. Experiments on GLM‑4.5 and Mixtral‑8×7B‑Instruct show significant throughput gains and reduced time‑per‑output‑token compared to existing inference engines, without compromising model quality.
By Qingxiu Liu, Yongchao He, Runhan Jiang, Zion Wang, Bohan Zhao, Mi Zhang, Patrick P. C. Lee