Bandwidth-Efficient Adaptive Mixture-of-Experts via Low-Rank Compensation
This addresses bandwidth efficiency for large-scale MoE models in inference systems, but it is incremental as it builds on existing offloading and quantization techniques.
The paper tackles the bandwidth and memory stress in Mixture-of-Experts models during inference by proposing a method that uses router-guided precision restoration with low-rank compensators, achieving a superior bandwidth-accuracy trade-off and improved throughput.
Mixture-of-Experts (MoE) models scale capacity via sparse activation but stress memory and bandwidth. Offloading alleviates GPU memory by fetching experts on demand, yet token-level routing causes irregular transfers that make inference I/O-bound. Static uniform quantization reduces traffic but degrades accuracy under aggressive compression by ignoring expert heterogeneity. We present Bandwidth-Efficient Adaptive Mixture-of-Experts via Low-Rank Compensation, which performs router-guided precision restoration using precomputed low-rank compensators. At inference time, our method transfers compact low-rank factors with Top-n (n<k) experts per token and applies compensation to them, keeping others low-bit. Integrated with offloading on GPU and GPU-NDP systems, our method delivers a superior bandwidth-accuracy trade-off and improved throughput.