arXiv AI
Oct 21

3D-MoE: Complementarity-Guided Hardware-Software Co-Design for MoE Decode on 3D-Stacked NMP

The paper introduces 3D-MoE, a hardware–software co‑designed system that optimizes Mixture‑of‑Experts (MoE) decoding on 3D‑stacked near‑memory processing (NMP) by exploiting expert complementarity. It groups experts offline, maps them locally to balance load, and uses a lightweight Collaborative Memory‑Network to stream hot expert weights, achieving an average 4.63× speedup over expert‑parallelism and 1.58×–1.86× throughput gains over existing NMP baselines with only a 2.11% area increase.

By Yudong Pan, Lian Liu, Shixin Zhao, Yintao He, Kaiyan Chang, Tianhua Han, Chenyang Ai, Haonan Zhu, Mengdi Wang, Yinhe Han, Ying Wang
arXiv Machine Learning
6d ago

One-Sided Expert-Parallel All-to-All for Mixture-of-Experts Inference over NVLink

The paper introduces NVLinkOneSided, a one‑sided expert‑parallel all‑to‑all communication scheme for Mixture‑of‑Experts inference on GPUs connected via NVLink. By pushing tokens directly into target GPU buffers without metadata exchange and using grouped GEMMs to read them in place, the method reduces fixed‑cost latency, especially at small batch sizes. Two synchronization protocols—Fence for high throughput and Sentinel for low latency—enable the approach, which achieves 1.2–3.0× faster dispatch and combine than DeepEP and up to 2.4× faster MoE layers on Blackwell GPUs, outperforming DeepGEMM MegaMoE up to 128 tokens per GPU. The implementation is modular, agnostic to activation quantization, and easily integrable into inference frameworks.

By Bo Li, Chulian Zhang, Or Biri, Anthony Chang, Anton Korzh, Noam Duvdevani, XingFei Xi, Daniel Stokes, Zhenhuan Chen, Ludwig Schneider, Artem Y. Polyakov, Julien Demouth, Chandler Zhou
arXiv Machine Learning
Sep 14

Dynamic Expert Quantization for Scalable Mixture-of-Experts Inference

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 Machine Learning
1d ago

Fuse-All MoE Inference Kernel with Load Balancing on TPUs

Fuse-All MoE is a TPU kernel that fuses token collection, expert projections, gated activation, and output writes to improve Mixture-of-Experts inference. It keeps intermediate expert computation on chip and uses fixed token-slot destinations to allow dynamic scheduling and expert placement while preserving routing semantics. Experiments show the kernel reduces runtime for skewed workloads and lowers latency, boosting overall serving throughput by up to 34.5% compared to the Megablox EP16 baseline.

By Rupeng Liu, Bangsheng Tang, Zongwei Zhou, Chengji Yao, Yejin Lee