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.
Abstract
Attention-FFN disaggregation maps LLM modules to specialized pools, creating an opening to keep Mixture-of-Experts (MoE) weights resident in a high-bandwidth FFN pool. Decode SLOs, however, cap the run-batch while sparse routing expands the activated-expert union, so weight traffic amortizes poorly and routing skew idles cold-expert resources. The FFN pool must therefore deliver weight-read bandwidth density under sparse unions and recover occupancy under skew without a global sharing fabric. We present a ReRAM near-memory architecture that keeps expert weights resident behind high-bandwidth local reads. The design factors actual MFU into ideal MFU and occupancy, recovers occupancy with bounded core-local multicast pooling, coactivation-aware placement, and load-aware fetch, and sizes each communication level from induced demand. A measured + modeled study on Qwen3.5-35B-A3B, Qwen3.5-397B-A17B, and GLM-5.2 shows that side-4 pooling raises occupancy from 0.328 to 0.519 and, at iso-peak compute, lowers per-token FFN-pool latency by 9.5x versus H20 with 20x lower weight-movement energy; an H20-attention + ReRAM-FFN system reduces decode TPOT by 1.25-4.0x, 2.4-10.3x, and 2.5-10.4x versus a homogeneous H20 pool.
LLMs scale Mixture-of-Experts (MoE) parameters for superior intelligence, but massive weights and dynamic computation impede efficient serving. Existing instance-level prefill-decode disaggregation isolates the phases on separate full-model replicas. As MoE weights grow, each instance may span tens to hundreds of GPUs, making resource allocation increasingly coarse. Configured prefill-to-decode ratios thus often mismatch demand, overprovisioning one phase while overloading the other. Prefill-decode colocation avoids this duplication, but existing Green Context solutions partition each GPU by phase and fix phase resources during a kernel. They cannot track resource changes across operations or layerwise variation in routed expert load, causing head-of-line blocking or idle reserved resources. Partitioning every GPU also leaves each phase with fewer local resources, forces wider parallelism and more communication, and lets prefill and decode traffic interfere on the shared network. We present ExpertPlex, which shares massive MoE experts across phases while disaggregating lightweight attention modules. Expert sharing eliminates over 95% of duplicate model weights and multiplexes dynamically sparse computation, while attention disaggregation reduces attention communication cost. ExpertPlex further uses (1) adaptive persistent kernels to schedule dynamic expert computation at tile granularity for efficient, isolated execution; (2) attention-initiated MoE communication to avoid network interference and enable cross-phase communication-computation overlap; and (3) a tile-to-cluster model to optimize these mechanisms for maximum goodput. Experiments serving MiniMax-M2.7 and GLM-5.1-FP8 show that ExpertPlex improves goodput by up to 2.01$\times$ over instance-level prefill-decode disaggregation and 1.66$\times$ over prefill-decode colocation.
Bingya Wu, Chao Jin, Zili Zhang et al.· 0 citations
In prefill-decode (PD) disaggregated LLM serving, each request is assigned to a decode worker after prefill. Existing decode routers balance only load; for mixture-of-experts (MoE) models this is incomplete: equally loaded workers can differ in latency, since each decode step loads the weights of every distinct expert its batch activates. We present ELDR, an expert-locality-aware decode router for PD-disaggregated MoE serving. From a request's prefill expert activations, ELDR builds an expert signature predicting the experts it will activate during generation. Offline, balanced K-means partitions signature space across decode workers; online, locality-band routing sends each request to the least-loaded worker among those best matching its signature. A signature cache, co-indexed with the KV cache at KV-block granularity, keeps signatures exact under prefix caching. Implemented in vLLM and evaluated on deployments of up to 40 GPUs, ELDR reduces median TPOT by 5.9-13.9% over the strongest of four load-balancing baselines across three MoE models and two workloads, with model outputs unchanged.
CELLServe formalizes SLO-constrained joint resource provisioning as an optimization problem with a dedicated algorithm, and introduces an opportunistic instance merging strategy for decode phase functions to reclaim fragmented resources.
Zejian Wang, Nan Lin, Zinuo Cai et al.· ACM Transactions on Architec...· 0 citations
LLM serving systems are provisioned for peak load to meet strict latency targets, leaving substantial GPU compute idle whenever traffic falls below peak. We present DeltaServe, a host-agnostic co-serving design that converts this idle inference capacity into LoRA fine-tuning throughput while preserving inference service-level objectives (SLOs). DeltaServe integrates with existing inference engines through a compact hook interface that requires only multi-LoRA batching support. It exploits the shared execution structure of inference prefill and LoRA fine-tuning forward passes, and uses an SLO-aware scheduler to admit and execute fine-tuning only when sufficient inference headroom is available. The scheduler is driven by a CUDA-graph-aware latency model calibrated offline and refined online. We integrate DeltaServe with vLLM, SGLang, and S-LoRA. On a production trace from Company X, DeltaServe on vLLM delivers 2.9x higher fine-tuning throughput than LLMStation at 100% inference SLO compliance, versus 85% for LLMStation. It also achieves 39% higher fine-tuning throughput than a baseline running vLLM+torchtune, using no additional hardware and maintaining full SLO compliance.
Jiaxuan Chen, Jianshu She, Ye Yuan et al.· 0 citations
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.