HCRMap is proposed, a hot expert residency mapping framework for pressure-aware expert replica management in 3.5D MoE inference that dynamically determines which experts should be promoted, retained, demoted, or evicted and maps routed token groups to suitable resident replicas, thereby jointly mitigating communication, memory, and queue bottlenecks.
Abstract
Mixture-of-Experts (MoE) large language models (LLM) activate only a small number of experts during inference, but token routing introduces persistent expert hotness skew: a small set of hot experts continuously receives most tokens, while the remaining experts are lightly loaded. On 3.5D multi-chiplet systems, this skew not only causes compute imbalance but also amplifies pressure on communication, memory bandwidth, I/O, and execution queues. Therefore, the core problem is not simply to reduce token movement, but to dynamically place and reuse hot expert replicas across different memory tiers. This paper proposes HCRMap, a hot expert residency mapping framework for pressure-aware expert replica management in 3.5D MoE inference. Based on expert hotness, weight loading cost, migration overhead, and runtime resource pressure, HCRMap dynamically determines which experts should be promoted, retained, demoted, or evicted. It then maps routed token groups to suitable resident replicas, thereby jointly mitigating communication, memory, and queue bottlenecks. Experimental results show that HCRMap reduces end-to-end latency by 43.6% and 43.0% over Hydra in the prefill and decode stages, respectively; by 34.5% and 33.1% over MoEntwine; and by 46.7% and 46.0% over PIMoE.
A ReRAM near-memory architecture that keeps expert weights resident behind high-bandwidth local reads and recovers occupancy with bounded core-local multicast pooling, coactivation-aware placement, and load-aware fetch, and sizes each communication level from induced demand is presented.
Kunming Shao, Ming Zeng, Xin Yuan et al.· 0 citations
Chain-of-thought (CoT) prompting improves LLM reasoning by decomposing complex problems into intermediate steps, but its sequential nature increases decoding latency and memory usage. Mixture-of-Experts (MoE) models scale capacity through sparse expert activation, yet their full expert weights often exceed GPU memory and require costly GPU-CPU transfers. Existing runtimes treat all tokens uniformly, overlooking a key structural property of CoT traces: consecutive reasoning stages exhibit coherent and predictable expert activation patterns. Ignoring this stage-level regularity leads to inefficient caching and unnecessary data movement. We propose SAEM, a stage-aware MoE inference runtime that detects reasoning stage boundaries and exploits stage-level activation coherence to guide expert placement. SAEM combines stage-aware caching, expert-aligned token repacking, and in-situ CPU execution to reduce data transfer and kernel fragmentation. On mathematical and scientific reasoning workloads, SAEM achieves an average 1.33x throughput improvement over the strongest state-of-the-art caching and offloading baselines under constrained GPU memory, rising to 1.54x when calibration data matches the workload, demonstrating the effectiveness of stage-aware, locality-driven MoE inference for CoT reasoning.
With a trace-driven, event-atomic simulator over three MoE models, a large offline-optimal gap substantially overstates the gains recovered by representative lightweight causal mechanisms.
EPIC mitigates imbalance via performance-aware expert migration and runtime expert activation, and then improves communication with topology-adaptive transport kernels and fine-grained computation-communication overlap.
Jiamin Cao, Qingxu Li, Yaozhong Liu et al.· Proceedings of the ACM SIGCO...· 0 citations
Mixture-of-Experts (MoE) models improve scaling by activating a small number of experts per token. However, the combined memory requirements of all experts may exceed the GPU's available high-bandwidth memory (HBM) during inference. Inference frameworks such as vLLM and HuggingFace address the problem by offloading experts to CPU memory and moving them to the GPU's HBM as needed. While enabling inference of large models with limited HBM, this CPU-GPU traffic overhead slows down token generation. We present PRED-MoE, a novel prefetching and eviction framework for MoE offloading. PRED-MoE uses a lightweight predictor to assess which experts are most likely to be required for prefetching and ranks experts by their near-future activation likelihood for eviction. Preliminary evaluation over the Qwen3-30B-A3B model and the MMLU-Pro dataset indicates that PRED-MoE reduces the TPOT of vLLM and HuggingFace by up to 3.02× and 28.62× respectively.
Wenchen Han, S. Vargaftik, Michael Mitzenmacher et al.· Proceedings of the ACM SIGCO...· 0 citations