Mixture-of-Experts Inference

Deploying Mixture-of-Experts (MoE) models relies heavily on Expert Parallelism, which generates intense inter-GPU communication. Consequently, state-of-the-art inference systems require high-bandwidth, P2P interconnects (e.g., NVLink) in datacenter GPUs to handle massive token routing, making deployment prohibitively expensive. Consumer GPUs offer comparable compute power at significantly lower cost, promising to democratize MoE inference for individuals and enable privacy-preserving local deployments. However, their bandwidth-limited (only weak PCIe bus bandwidth) and host-mediated interconnects (no P2P support) introduce severe communication bottlenecks. We present CoMoE, a communication-efficient MoE inference system that resolves this mismatch through novel host-centric routing. Our key insight is that the unique communication topology provides the opportunity to elevate the host to an active routing hub, which can fundamentally reduce communication volume and eliminate global synchronization-induced stalls. Specifically, for token dispatch, we introduce host-backed token multicast to write shared tokens to the host exactly once, eliminating outbound transmission redundancy. For token combine, we propose a fine-grained, token-level aggregation mechanism using host staging buffers, which replaces rigid global synchronization and mitigates straggler effects. Evaluation on RTX 5090 GPUs shows that CoMoE improves inference throughput by up to 1.46x, approaching the performance of NVLink-capable A800 GPUs at only 23.4% of the hardware cost.

Mixture-of-experts (MoE) routers typically apply softmax to the router scores and keep the top-K experts, making every token use exactly K experts. Sparsity-inducing probability maps such as sparsemax, alpha-entmax and normmax can adaptively assign exact zeros to selected experts, and therefore appear to offer token-dependent expert participation, even when using the same top-K machinery. In this work, we study whether and how this sparsity survives training. We train matched 300M and 1B top-2 MoE language models with softmax, 1.5-entmax, sparsemax and 2-normmax, and find that the maps behave very differently once trained: at 1B, entmax discards 30% less probability mass than softmax while almost never dropping a selected expert, sparsemax retains the most mass, and normmax routes 21% of tokens to a single expert. These outcomes are not properties of the maps alone. Each map drops a selected expert only when the gap between the two largest scores reaches a fixed threshold, and the trained routers differ in the score distribution they learn: the entmax router learns scores with roughly half the spread of softmax's, which keeps its top-2 gaps below its threshold, while sparsemax and normmax, which share the same threshold, learn different gap distributions and hence different participation. Routers thus co-adapt their scores to the map, and a map's capacity to produce zeros does not by itself determine expert participation. While none of the sparse maps improves validation loss over softmax, they make the trained models far less sensitive to selecting more experts at inference: sparsemax trained with K=2 loses 0.02 nats when run with K=8, where softmax loses 0.58. Our results indicate that adaptive MoE routing has to be designed around the joint behavior of the probability map and the learned scores, rather than around the map alone.

Mixture-of-Experts (MoE) Diffusion Language Models (DLMs) offer flexible parallel decoding and increased model capacity, but their large number of expert parameters incurs substantial computation and storage costs. Existing low-rank MoE compression methods largely rely on static factorization and fixed rank allocation, which overlook the distinctive properties of MoE DLMs. Specifically, we identify two properties: cross-mode non-uniform redundancy, where parameter redundancy and sensitivity to rank truncation vary across the input, output, and expert modes, and token-wise utilization variation, where hot and cold tokens exhibit distinct spectral characteristics and expert activation patterns. To address these challenges, we propose ITC-MoE, an Importance-guided Token-aware Compression framework for MoE DLMs. ITC-MoE consists of two complementary components. First, Importance-guided Adaptive Tucker Compression (IATC) incorporates activation and gradient importance into expert weight transformation, jointly factorizes expert weights across multiple modes, and adaptively allocates ranks under a fixed parameter budget. Second, Token-aware Compensation and Routing (TCR) applies lightweight low-rank compensation to compression-sensitive hot tokens and restricts the candidate expert set for cold tokens with concentrated routing patterns. By jointly adapting compression capacity and inference execution to both parameter redundancy and token-wise variation, ITC-MoE substantially reduces the computation and storage costs of MoE DLMs while preserving their generation quality. For example, on SDAR-30B-A3B-Chat-b32, ITC-MoE maintains an accuracy of 96.33% on MultiArith under a 30% compression budget, while achieving up to a 7.22x end-to-end speedup. The code is publicly available at https://github.com/lianjunl13-sudo/ITC-MoE.

Expert parallelism (EP) enables inference of large Mixture-of-Experts (MoE) models by placing their experts across multiple GPUs, but requires substantial communication between GPUs at every MoE layer. As contemporary MoE models activate more experts per token, this communication accounts for a growing fraction of inference time. The cost becomes particularly pronounced on PCIe-based consumer GPU systems, where all inter-GPU transfers traverse CPU memory. However, existing MoE-specialized EP communication libraries assume that direct GPU-to-GPU access is available, largely overlooking consumer GPUs. Therefore, most LLM frameworks instead rely on NCCL, whose CPU-staged communication incurs redundant PCIe transfers and competes with expert computation for GPU resources, limiting their overlap. We present ThunderEP, a novel communication design for such systems that removes the relay hops of traditional ring algorithm, moves data through DMA engines to avoid compute resource contention, and minimizes synchronization latency by reducing the polling overhead of completion flags in CPU memory. We integrate the proposed design into vLLM and evaluate it on three widely used MoE models. Experiments on two PCIe systems equipped with RTX 4090 and RTX 5090 GPUs show that ThunderEP achieves average speedups of 2.00$\times$ and 1.53$\times$ over NCCL for dispatch and combine, respectively, and up to 1.66$\times$ end-to-end speedup over state-of-the-art MoE inference frameworks.

Multimodal mixture-of-experts (MoE) models combine sparse expert activation with visual-language capabilities, yet their inference remains costly because long visual-token sequences repeatedly incur attention, routing, dispatch, and expert-MLP computation. Existing methods typically compress either the token or expert dimension, leaving redundancy along the other. Our analysis reveals two complementary regularities: the depth required for visual propagation varies across inputs, while text-token routing exhibits concentrated and recurrent expert-importance patterns. Based on these observations, we propose DecoMoE, a two-dimensional structured compression framework that decouples visual propagation from expert computation. The Sample-Adaptive Visual Boundary (SAVB) predicts an input-dependent visual-exit layer at which the visual-token block is removed. The Routing-Calibrated Expert Prefix (RCEP) reorders experts offline using text-token routed mass and, from this predicted exit layer onward, retains at each MoE layer the shortest contiguous prefix covering a target routed-mass fraction. We evaluate DecoMoE on Qwen3-VL-MoE and InternVL3.5-30B-A3B across six benchmarks. On Qwen3-VL-MoE, DecoMoE retains 97.91% of dense-baseline performance while reducing computation from 27.06 to 16.73 TFLOPs and latency from 0.44 to 0.26 seconds, yielding a 1.69x speedup. Code will be available at https://github.com/ShawnTan86/DecoMoE.

Mixture-of-Experts (MoE) layers are central to frontier language models, and recent architectures push toward more and smaller experts. In this regime, the standard linear router becomes a bottleneck: with $M$ experts and hidden dimension $h$, its per-token cost $Θ(Mh)$ dominates the MoE layer once $M$ is large. We introduce MoRE (Mixture of Rank-reduced-routed Experts), which factorizes the router weight matrix at rank $r$ and reduces the routing cost to $O((h + M)r)$. We prove that rank logarithmic in $M$ suffices for routing expressivity when the number of active experts is fixed, and is necessary up to precision factors. We also prove that logarithmic rank preserves load balance in a Gaussian memorization model, and training on a synthetic phonebook task shows that low rank does not hurt memorization. At matched active FLOPs, the factorization allows a factor of $Θ(h/r)$ more experts. To realize this gain in wall-clock time, we design a fused Triton kernel at inference that avoids expensive memory operations on HBM. Empirically, MoRE improves memorization on the phonebook task and performance on knowledge-intensive Q&A benchmarks after pretraining, while matching reasoning ability. Code available at https://github.com/Matheart/MoRE_code.

Mixture-of-experts (MoE) models activate few experts per token, yet batched decoding can access nearly the entire expert pool, making expert-weight traffic a major bottleneck. Expert pruning reduces this traffic, but conventional approaches also prune compute-bound prefill, sacrificing model quality for little throughput benefit. We present SlimWise, a serving framework that tailors the expert pool to each inference phase. SlimWise performs prefill with the full model and decode with a pruned model that directly reuses the prefill-generated KV cache without conversion. Across two MoE backbones and three pruning criteria, this training-free KV cache handoff substantially narrows accuracy gaps relative to the full model in many settings. We also show that benchmark accuracy can conceal substantial pruning-induced changes in generation length. To address these distortions and residual accuracy loss, SlimWise introduces a low-cost distillation stage that trains the decoder to continue from full-model KV caches while updating only a small subset of parameters. Implemented in vLLM, SlimWise supports both prefill-decode (PD) disaggregation and PD-colocated serving. On Qwen3.6-35B-A3B, SlimWise improves decode throughput by up to 1.81x at 50% expert pruning with minimal accuracy loss.

Mixture-of-experts (MoE) language models often exceed the memory of a single GPU. Expert offloading keeps most experts in host memory and loads them on demand, so decoding speed depends on how many experts each token must fetch. Caching and prefetching reduce this cost only as far as the routing allows. Router-only fine-tuning can reshape the routing to reuse experts, but it keeps the experts frozen, so they cannot adapt to the tokens the new routing sends them. We propose MaskCoFT, a masked co-adaptive fine-tuning method that trains routers and experts together with the cross-entropy loss alone. During fine-tuning, a learnable binary mask restricts the Top-K routing of each layer to a subset of experts, and the experts adapt to the tokens redirected to them. At inference, the learned mask becomes a soft prior that re-ranks experts, so every expert remains selectable. We simulate a GPU cache of 4 experts per layer for Mixtral-8x7B and 12 for DeepSeek-V2-Lite. MaskCoFT cuts expert fetches per token by 23.7% and 10.1% relative to the base model. In real offloading system serving, it lowers the time per output token by up to 16.4% and 5.5%, respectively. Its average accuracy over nine benchmarks stays above the base model by 0.92 and 0.53 points.

Subject-independent motor-imagery (MI) EEG decoding can exhibit subject-level failures even when average performance appears acceptable: under subject shift, a decoder can become an overconfident near-one-class predictor. This is especially problematic in source-free deployment, where target-user labels are unavailable during adaptation and expert selection. We present \textit{EEG-Fusion}, a failure-informed decision-level fusion framework that treats source-free MI decoding as label-free reliability estimation over heterogeneous experts. EEG-Fusion applies subject-wise Euclidean alignment and normalization-only test-time adaptation, then routes each target subject to a neural, covariance-based, or physiological-feature expert using a reliability gate trained on source-held-out folds to predict expert performance and collapse risk from label-free stream diagnostics. The gate uses confidence, entropy, prediction diversity, expert agreement, and predicted class balance; collapse is measured as the maximum predicted class fraction. In 9-fold leave-one-subject-out (LOSO) evaluation with three seeds, relative to a no-alignment raw EEGNet source-free anchor, EEG-Fusion improves subject macro-F1 from 0.417 to 0.529 on BCI IV-2a local protocol, from 0.314 to 0.482 on BNCI2014-001, and from 0.607 to 0.708 on BNCI2014-004; corresponding collapse-index reductions are 0.199, 0.227, and 0.169. In a 9-subject Cho2017 external subset, EEG-Fusion improves macro-F1 from 0.516 to 0.630. These results suggest that label-free reliability estimation can reduce subject-level failure modes in source-free MI-EEG deployment.

Mixture-of-Experts (MoE) models have emerged as a revolutionary method to scale Transformer models. However, traditional MoE architecture still suffers from inefficiency since a large number of experts are unnecessarily activated. Existing approaches for reducing the number of activated experts often overlook the historical performance of each expert. In this paper, we propose EAT, a novel method called Expert Account Tracker (EAT), which utilizes history-awareness metrics and adaptive thresholding to dynamically select the most important experts, thereby reducing the activated expert number while effectively maintaining the model performance. Experiments show that EAT outperforms the existing baseline Top-P method across multiple models and datasets, achieving over 25% an average reduction compared to the vanilla method in the number of activated experts and performing better token generation speed compared to the baseline. Furthermore, the performance of pruned models can be efficiently recovered via OPD using only 9K data. Additionally, through ablation studies, we find that excessively reducing the number of activated experts can significantly harm model performance, and the importance of experts varies across layers, with higher-level experts being generally more critical.

Semi-autoregressive diffusion large language models (dLLMs) improve decoding parallelism through iterative block-wise denoising, but scaling them with mixture-of-experts (MoE) layers introduces a large expert parameter footprint that exceeds memory-constrained GPU capacity. Expert offloading is a natural remedy, yet existing MoE serving systems target autoregressive decoding and rely on intra-iteration layer-wise prefetching: while computing one layer, they predict and load experts for subsequent layers. Under dLLM inference, block-wise routing expands the active expert working set within each iteration, making such prefetches difficult to complete in time and costly when mispredicted. Consequently, existing prefetch-based solutions often degenerate into on-demand expert loading with high decoding latency. We propose OLED-MoE, an expert offloading system that shifts the optimization target from intra-iteration prefetching to inter-iteration expert retention. Its key insight is that adjacent denoising iterations exhibit strong expert routing overlap, and token confidence indicates which experts are likely to be reused. OLED-MoE uses confidence-guided inter-iteration prediction to retain high-value experts in GPU memory without introducing extra prefetch traffic. It further compensates unavoidable cache misses through CPU-GPU cooperative execution, jointly considering dynamic expert computation load and predicted future reuse. Across diverse dLLM workloads, OLED-MoE reduces time per output token (TPOT) by 1.23x-7.93x and improves expert cache utilization by 1.44x-4.23x over state-of-the-art offloading systems. Notably, OLED-MoE approaches full-residency performance while using only 40% of the expert GPU memory, incurring merely 23% higher TPOT despite a 60% reduction in expert memory footprint. OLED-MoE's source code is publicly available at https://github.com/flashserve/OLED-MoE.

Sparse activation reduces mixture-of-experts computation without eliminating the need to store all experts. We present Routide, a Swift/MLX runtime that executes the text path of a pinned public Qwen3.6-35B-A3B quantized checkpoint while keeping expert weights in iPhone storage and a byte-budgeted subset in memory. We characterize cache-policy sensitivity, numerical comparison boundaries, and measurement limits. Across five recorded 128-token workloads, fixed-route replay gives 0.00% demand hits with a 512 MiB LRU cache, 18.80% with seeded random eviction at the same budget, and 38.58% with 576 MiB LRU. The apparent capacity cliff is therefore a policy/workload interaction, not a universal memory requirement. Same-runtime Mac controls preserve generated sequences across eviction and asynchronous prefetch, including 2,560 exact token comparisons and 10,334 speculative loads. In contrast, complete resident-Python versus recorded-phone sequences disagree on all five tested cases, precluding a general numerical equivalence claim. Two separately scoped iOS 27 memory protocols observe sampled process-footprint peaks of 1.87-2.32 GiB on short prompts and 2.39-2.73 GiB on one longer prompt. We retain a thermal stopping event, negative timing comparisons, and a single qualified whole-device power estimate. These results establish bounded feasibility and identify limitations that a deployment claim must not hide.

Fine-grained mixture-of-experts (MoE) architectures have become a mainstream design for open-weight LLMs, with hundreds of experts and increasingly many selected per token. This shift makes dynamic expert pruning an attractive route to cheaper inference. Yet existing evidence comes largely from coarser architectures and likelihood-scored multiple-choice benchmarks, leaving three central questions open in the fine-grained regime: how redundant per-token expert selection is, how effectively existing pruning methods exploit that redundancy, and what governs a model's sensitivity to pruning. We fill this gap with a systematic empirical study of twelve fine-grained MoE checkpoints spanning nine architecture families, with a core suite of eleven benchmarks covering knowledge QA, mathematics, code generation, and general reasoning. We find that expert selection is far more redundant than the field's operating points assume: uniformly retaining about two thirds of the selected experts preserves 98.8% of unpruned performance on average, requiring only a one-integer change and delivering 1.2-1.7x measured speedup across two serving backends. This simple baseline leaves little room for dynamic allocation at conservative budgets: even the best published rules differ from it by under 1% at matched expert budgets. Their value emerges under aggressive pruning, where the best rules recover up to 3.0% over uniform truncation, with gains concentrated in the generative tasks that suffer the sharpest degradation. Sensitivity to aggressive pruning also depends on the model: larger and thinking models are more resilient, whereas multimodal models are more vulnerable. Together, these findings reveal how much expert computation fine-grained MoEs can dispense with, and establish when dynamic allocation earns its complexity, informing both practical deployment and future pruning methods.

Mixture-of-experts (MoE) inference on consumer hardware is bounded by weight memory: a 35B-class model is 19.5GB at 4-bit, and sparsity shrinks the compute per token, not the bytes that must be held. Naive offloading to SSD does not help on its own, because layer N+1's experts must be chosen before layer N's output exists, so the reads cannot start early enough to hide behind compute. We present Edge0, a streaming MoE inference engine that closes the gap with a prerouter: a per-layer head predicts the next layer's routing one token ahead, and the prediction is consumed as the routing itself, so the staged expert set equals the routed set and nothing is dropped. An unmerged recovery LoRA, trained on the student path, pays back the quality lost to int4 quantization and routing replacement. On a single 24GB machine, Edge0 serves a 35B MoE at 20tok/s inside 3GiB of peak active memory, within a few points of its fp16 teacher on average across five public benchmarks. An 8B tier runs on the same framework, and the framework, checkpoints, and adapters are open source.

A document modeled as a discrete sequence of tokens can be thought of as being generated from a composition of texts from different domains; a README file, for example, moves between prose, code, and configuration. When such a document is corrupted and only frozen domain experts are available, restoring it requires deciding both what is missing and which expert to trust at each position, at test time and without region labels or a trained router. We introduce evidence-aligned local composition, which infers a soft, position-wise weighting over the experts from the marginal evidence of the corrupted observation under a given corruption model, estimating the evidence from the experts' own denoising losses and smoothing the weights across positions. Because the weighting is soft, it recovers a mixture when the true composition is mixed and concentrates on one expert when that suffices. Across a categorical simulator, byte-level experts, and experts fine-tuned from a $1.3$B discrete flow-matching model, the inferred weights track the true regions at $0.85$ field accuracy on naturally mixed scientific documents, and at $0.98$ on constructed mixtures whose regions are lexically disjoint. Restoration improves over a single global weight when the experts are genuinely distinct and reduces to it when they converge, tracking a measure of expert separation.

Quantized Mixture-of-Experts (MoE) services can hold several pre-materialized instances of one base model, but quantization damage varies sharply across requests and bitwidths. Because instance materialization and replica counts consume memory and require slow reconfiguration, we treat them as upstream provisioning decisions and study routing within a fixed resident pool. Within this fixed-pool boundary, we route each request to maximize modeled throughput under a class-level expected quality-degradation budget and measured instance capacities. To predict this request-specific risk, we introduce FWP (Fragility-Weighted Perplexity), computed from prompt tokens on a reference-instance prefill and calibrated to candidate-instance degradation. Underlying FWP is an exact two-expert affinity--fragility decomposition and a conditional multi-layer top-$k$ expansion whose bias, interaction, route-change, separability, and higher-order terms remain explicit. Using these calibrated risks, a window-level linear program yields a signed reduced-reward score that is KKT-consistent with the LP optimum under optimal prices and primal-feasible tie allocation. On 88 extended Qwen prompts, complete W2, W3, and W4 instances quantizing all 6,144 expert blocks incur mean $\Delta$NLL of $0.9437$, $0.1832$, and $0.0513$. Under the same population and $\tau=0.1513$, FWP allocation reaches a $1.284\times$ offline model-based multiplier versus $1.253\times$ for request-agnostic mixing and $1.000\times$ for static W4, an incremental $2.5\%$ relative FWP gain.

Mixture-of-Experts (MoE) creates a structural advantage for offloading: only a small fraction of activated experts need to reside in device memory, and if they can be loaded in time for computation, offloading can in principle approach full-load performance, where all model weights reside in device memory. Yet translating MoE's structural advantage into practical offloading gains remains challenging. We propose SeqMoE to bridge this gap. To maximize expert hits, we build predictive memory management: (i) Sequence-to-sequence prediction. We are the first to recast expert activation prediction as sequence modeling, enabling accurate multi-step, multi-layer forecasts that provide a long and reliable window for downstream decisions. (ii) Joint prefetch scheduling. We formulate prefetch scheduling as Job Sequencing with Deadlines to maximize expected expert hits and improve bandwidth efficiency. (iii) Forecast-driven caching. Leveraging the recursive nature of sequence modeling, we introduce a probabilistic Belady policy for future-aware eviction. To eliminate execution bottleneck, we develop (iv) Graph-compatible offloading runtime. We derive general runtime principles encompassing compute-transparent expert placement and synchronization-free orchestration disciplines for end-to-end graph capture. With 45% expert residency, SeqMoE averages a 96.97% hit rate and 80.22% of full-load performance, advancing the state of the art in MoE offloading.

Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling model capacity while preserving efficient inference in large foundation models. However, most MoE models use a fixed top-$k$ expert selection policy, assigning the same expert budget to every token even when fewer experts may be sufficient. Inference-time dynamic top-$k$ routing can reduce computation without retraining, but existing methods often overlook the distributional shift caused by deviating from the training-time routing configuration. We show that reducing the number of activated experts consistently increases the RMS scale and variance of SMoE outputs, inducing a representation mismatch that contributes to downstream performance degradation in addition to the loss of expert capacity. To address this correctable component, we propose Layer-wise Distribution Alignment (LDA), a lightweight inference-time correction that uses layer-wise calibration statistics to align reduced-routing representations with the default configuration. Across multiple SMoE LLMs, benchmarks, and routing strategies, LDA recovers much of the performance lost induced by the distributional shift under reduced routing while preserving sparse-inference efficiency with negligible overhead.

Mixture-of-Experts (MoE) architectures scale Large Language Model (LLM) capacity efficiently by activating a sparse subset of experts per token. However, modern MoE inference remains heavily constrained by the rigid, whole-expert abstraction. Existing frameworks manage, schedule, or prune experts as atomic execution units, which fixes the optimization boundary too early and leaves fine-grained intra-expert computational redundancy underexplored. In this work, we present PCoMoE, a path-compositional execution framework that shifts MoE inference from coarse-grained expert selection to fine-grained path composition. PCoMoE incorporates a path-level formulation of expert computation, a compatibility-aware layer-wise pruning strategy to suppress low-value path combinations, and a hardware-friendly execution engine to exploit reusable sub-expert structures under strictly bounded overheads. Experimental results demonstrate that PCoMoE achieves up to a 1.31x end-to-end inference speedup while enhancing model accuracy by 10%. The code is available at https://github.com/gzyyy0/PCoMoE

Mixed-format medical visual question answering (VQA) requires stable option selection and machine-readable free-text output. The two formats fail differently: multiple-choice predictions can change with option symbols or positions, while clinically plausible open answers can fail automated evaluation when serialization is malformed. We address both challenges with an answer-text memory, a permutation-stabilized vision--language expert, and a sparse candidate- expanding router. The cyclic schedule follows prior work; our contribution is to make expert top-2 a routable candidate alongside memory and expert top-1. On a 1,403-case retrospective internal analysis, this expansion improves a matched binary router from 88.95% to 91.73% (+2.78 percentage points; 95% CI 1.57--3.99), with 56 rescued errors and 17 regressions. Oracle coverage rises from 90.31% to 96.15%, and the final submitted configuration reaches 92.23% on the same retrospective split. For open questions, strict generation and deterministic guards produce 475/475 schema- valid participant-facing outputs without repair, retry, or hard-gate failure. Visual ablations reveal substantial textual dependence. Candidate expansion supplies the principal controlled routing gain; open-path evidence establishes output-contract validity rather than clinical correctness in medical use or deployment.

Mixture-of-Experts (MoE) models enable efficient scaling of large language model (LLM) inference but suffer from substantial data-movement overhead when deployed on neural processing unit (NPU)-based systems. Near-Data Processing (NDP) provides a promising way to mitigate this bottleneck via cooperative NPU-NDP execution. However, existing NPU-NDP MoE systems do not fully account for hardware heterogeneity, dynamic expert-level concurrency, and temporal expert reuse during batched inference. This paper presents DynaNDE, a dynamic near-data expert scheduling framework that exploits NPU-NDP collaboration to accelerate batched MoE inference. DynaNDE introduces an analytical performance model that captures hardware heterogeneity, data-movement costs, and communication-computation overlap in cooperative NPU-NDP execution. Guided by this model, DynaNDE determines per-layer expert scheduling across the NPU and NDP while accounting for expert-level concurrency. DynaNDE also incorporates a reuse-aware runtime that avoids redundant parameter movement when experts reside in NPU memory. Experimental results show that DynaNDE achieves substantial throughput improvements over the state-of-the-art NPU-NDP MoE serving framework, with average speedups of 2.6$\times$ and 2.2$\times$ for the prefill and decoding stages, respectively.

In expert-parallel (EP) MoE serving, every layer synchronizes at the slowest GPU. Dispatchers balance token counts (EPLB, LPLB, UltraEP) or activated-expert counts (METRO), assuming expert time is linear in one. Measurements on two datacenter GPU generations show it is neither: below $\nstar\!\approx\!156$--$168$ tokens, HBM weight streaming dominates---cost attaches to \emph{activated replicas}, not tokens; above it, grouped GEMM rounds tokens to 128-tile $M$-tiles, so \emph{splitting} an expert adds padded compute. A max-affine profile $t=\max(a+bG,\,c+βN)$ captures both regimes. Realistic decode batches hold hot experts in the linear regime and cold in the flat \emph{simultaneously}; recorded batches show proxy dispatches differ by $1.4$--$1.6\times$ in modeled block time (p95 up to $1.7\times$), and \emph{which} proxy wins flips with the regime. We formalize per-batch dispatch as a fixed-charge makespan problem---NP-hard on two fully replicated GPUs, polynomial in degenerate limits---and present \sys{}, a makespan-aware dispatcher solving it in milliseconds off the critical path; its SGLang integration runs out-of-process and fuses dispatch with count collection into one in-graph kernel. Anchored by an 8-GPU TestbedA microbenchmark, \sys{} stays within 1% of the best fixed baseline everywhere and wins by up to $15.5\%$ where regimes mix. End-to-end on TestbedB, Qwen3-235B (inside the win region) gains $4$--$6\%$ throughput and cuts p99 latency by ${\sim}15.6\%$; DeepSeek-V3 (outside, communication-dominated) shows only mechanism cost. A phase diagram, not a universal win, is the claim: it predicts both outcomes before deployment.

Mixture-of-Experts (MoE) models are attractive for edge deployment because they provide high model capacity while activating only a small subset of parameters per token, improving compute efficiency. However, MoE inference at the edge is fundamentally limited by memory. Expert parameters are large and often reside in off-chip memory due to capacity, cost, and power constraints, putting expert loading to the critical path. We present APEX: Adaptive Expert Prefetching, a predictive resource management framework that overlaps expert loading with useful computation. APEX introduces a lightweight prefetch router that predicts candidate experts before the attention block to dynamically fetch additional experts using a learned confidence model. This adaptive strategy achieves over 99% overlap accuracy, significantly outperforming fixed top-k prefetching techniques. APEX supports two execution modes: a correctness-preserving mode that guarantees exact routing semantics, and a stall-free mode that eliminates residual stalls by operating on available experts with negligible impact on application accuracy. Across multiple MoE models, the correctness-preserving mode reduces per-token latency by up to 26% and improves energy-delay product (EDP) by up to 41% over state-of-the-art baselines, while the stall-free mode provides additional efficiency gains with negligible impact on application accuracy. These results establish adaptive, confidence-driven expert prefetching as an effective approach for efficient MoE inference on edge systems.

Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts. Shared-expert designs preserve reusable knowledge, fine-grained methods vary computation within experts, and dynamic routers adapt the number of active experts. Yet these decisions are usually made independently, overlooking a basic dependency: extracting reusable computation changes both what remains and how much expert capacity the remainder needs. We study this dependency by decomposing sparsely upcycled feed-forward experts into key-value channels. Co-activated experts align at a subset of value positions; removing these positions changes expert preference; and greater shared coverage is associated with lower residual expert demand. These observations lead to one principle: share first, then route what remains. We instantiate it in UniF-MoE, a unified framework for token-adaptive MoE computation. Each expert is partitioned into aligned blocks. A shared-demand score sets the shared block count and pathway weight, key prototypes select the shared content, and the complementary demand determines the residual expert count through cumulative routing mass. A Gram regularizer separates and normalizes router embeddings, promoting diverse routing directions, sparse expert overlap, and a simple routing geometry. Experiments on DomainBed and GLUE show that this unified design improves predictive performance over representative static and dynamic MoEs while reducing activated computation, inference latency, and memory. Code is available at https://github.com/existence0420/UniF-MoE.

PTQTP decomposes LLM weight matrices into two ternary (trit) planes with two free per-group scales. Tying the scales to a fixed ratio of three collapses the decomposition into a single uniform nine-level quantizer, a known balanced-ternary identity. To our knowledge, at the time of writing, this work is the first to impose that identity as a constraint inside PTQTP's solver. The two trit planes then fold losslessly into one 4-bit code plane that we make the persistent serving representation: disk bytes, expert-cache bytes, and kernel input are the same 4.0625-bits/weight blocks, consumed in one integer dot pass. For this conjunction (ratio-3 nine-level code, CPU-SIMD kernels, SSD expert streaming, identical persistent bytes) we likewise found no precedent. We apply this to the routed experts of DeepSeek-V4-Flash-0731, a 284B-A13B mixture-of-experts model, quantizing in one shot from the released MXFP4 expert weights and streaming experts from SSD on a 64 GB laptop. Against a 4.5-bit Q4_K baseline, measured one process per fixture with an expert-lossless anchor arm as reference control, the tied model matches the official serving API on 5/5 fixtures at step 0 (Q4_K: 4/5) and 12/14 captured continuation steps (11/14), scores 86 vs. 84 on a 100-item MMLU subset, decodes 6.7% faster in decode phase, and ships 9% smaller files: no detected fidelity difference at these small evaluation sizes, and every fixture-level difference between the arms traces to a single measured near-tie cell. The tied fit nevertheless shows higher weight-reconstruction error and worse perplexity, a measured dissociation between proxy metrics and reference fidelity. A cumulative trunk-ternarization ladder and bitwise-pinned aarch64/x86-64 kernels complete the report. All code, formats, and evaluation artifacts are open source in the fucina inference stack.

Mixture-of-Experts models increase parameter capacity while keeping the computation activated by each token bounded, but their architectural evolution cannot be explained by a chronological list of model releases alone. This technical survey synthesizes primary papers, official technical reports, and prior surveys to organize modern Mixture-of-Experts systems along five coupled dimensions: expert granularity, expert topology, routing freedom, the scope of load balancing, and execution structure. We describe eight architectural milestones as a dependency graph with six mainline developments and two orthogonal branches, rather than as eight successive generations. We then analyze individual systems through four control planes: Expert Topology, Routing, Balance, and Expert Parallelism. These planes specify which experts exist, which experts process each token, how aggregate load is controlled, and how selected computation is mapped onto physical devices. The framework connects algorithmic choices such as Top-k routing, shared experts, fine-grained experts, and dynamic expert composition with systems concerns including token dispatch, device placement, all-to-all communication, and communication-computation overlap. We conclude with equal-budget pretraining experiments, quality and systems metrics, and open research questions. The main trend is a shift from merely activating more sparse parameters toward decoupling semantic routing, computational budgets, and physical execution.

Sparse mixture-of-experts (MoE) layers expand recommendation capacity through conditional computation, yet a trained checkpoint still stores and routes over its full expert bank. We study a deployment problem: convert that checkpoint to a smaller standard MoE under an explicit expert budget, without adding a compression-specific online module. To address this, we introduce UniMoMo, a post-training compression framework formulated as a constrained graph coarsening problem. Rather than relying on parameter distance, UniMoMo groups experts based on their functional similarity, using an unlabeled calibration set to measure how similarly experts respond to shared recommendation states. To prevent performance degradation, we introduce a layer-adaptive protection mechanism that restricts the merging of high-traffic experts based on their routing exposure. Across Amazon Beauty, KuaiRec, and TenRec with 2, 4, and 6 MoE blocks, the final four-expert checkpoints obtain source-relative five-run mean NDCG@10 ratios of 99.92%--102.30% and measured A100 speedups of 1.28$\times$--1.63$\times$. An aggressive two-expert, top-1 operating point obtains ratios of 98.36%--104.24% and speedups of 1.47$\times$--2.21$\times$. These endpoint results evaluate the complete conversion-and-adaptation workflow and show that a trained recommendation MoE can be exported at multiple serving budgets.

Load Balancing has emerged as a critical problem in expert-parallel distributed inference of Mixture-of-Experts (MoE) models. As routing distributions are typically skewed across experts, devices hosting lighter-loaded experts must idle to wait for the heaviest during expert computing, leading to inefficiency. Existing load-balancing approaches primarily rely on expert replication or migration within each layer, which introduce additional overhead and limit their flexibility and scalability. To address this problem, we propose EasyBalance, a cross-layer load balancing strategy that requires no modifications to the expert-device mapping, enabling instant adaptability and incurring essentially no additional overhead. Our key insights are that (1) experts of other layers can be viewed as naturally redundant for the current layer, and (2) cross-layer MoE workloads can be jointly executed to mitigate their individual imbalance. Based on these observations, EasyBalance greedily schedules a subset of cross-layer workloads to run at each MoE step and defers the remaining workloads for future balancing opportunities, effectively leveraging cross-layer imbalance mitigation. Extensive experiments across models, tasks, and configurations demonstrate that EasyBalance consistently accelerates distributed MoE inference, reducing GPU idling by mostly over 40%. Code is available at https://github.com/yize-wu/EasyInfra.

Mixture-of-Experts (MoE) models have outgrown accelerator memory, and offloading expert weights to host memory is now standard. This makes expert cache management an attractive lever: a policy that raised the hit rate would cut expert traffic per token. Evaluating that is a measurement problem, and we find the measurement fragile. With a trace-driven, event-atomic simulator over three MoE models (40, 64, 128 experts), we isolate three evaluation axes that change conclusions, not just numbers. Replay semantics: under a fused-event traffic contract, an inconsistent per-access replay inflates recency-based policies by 27-29% while leaving frequency-based and static ones within 4%, inverting the policy ranking. Workload contamination: probe sets using one instruction template per category produce verbatim-identical generation prefixes; a matched-pair rendering intervention moves the measured early-window effect by 19.4-31.9 points and reverses which workloads look most cache-friendly. Operating regimes: normalized miss fractions do not transfer across models, so the per-step expert union relative to per-layer capacity must be reported -- yet permuting only the temporal order of an identical event stream moves the offline-optimal gap from 44.9% to 30.8%, so it is not sufficient. Corrected, a stable gap to the offline optimum remains (44.2-45.9% over 13 frozen workload compositions). A forced-admission oracle attributes 84.3-96.6% of it to knowing which resident expert is used furthest in the future. A causal next-use predictor, used as an eviction rule, recovers -11.4% of the gap; it picks an optimal victim 3.4% of the time, against 2.4% for a random resident block and 20.6-22.1% for LRU and LFRU. Our position is narrow: in our evaluated settings a large offline-optimal gap substantially overstates the gains recovered by representative lightweight causal mechanisms.

Mixture-of-Experts (MoE) language models deliver high capacity at low per-token compute, but deploying them cheaply requires compressing their many expert weight matrices. Expert pruning (e.g., REAP) and merging reduce cost but sacrifice accuracy and require retraining the router; low-rank delta decomposition of experts (e.g., D^2-MoE) preserves all experts and the router, but degrades sharply as the expert count grows because a single shared component cannot approximate many near-orthogonal experts. Because MoE expert weights are near-orthogonal, a single shared component (as in prior delta decomposition) scales poorly with the expert count; we show that experts nonetheless organize into functional co-activation communities that are decoupled from weight similarity. Building on this, we introduce LorExperts, a router-preserving compression method that clusters experts, keeps one full-precision dominant per cluster, and represents the remaining members as low-rank corrections to their local dominant. LorExperts retains all experts and the original router (no router retraining). At ~50% expert compression on Qwen3-30B-A3B and Gemma-4-26B-A4B, LorExperts preserves downstream accuracy and perplexity better than the baselines on most of the tasks; the margin over D^2-MoE grows with expert count E. We further give a reconstruction fine-tuning procedure for LorExperts, and BTExperts, a tree organization of dominants and corrections that enables inference-time amortization of shared computation.