Diagnosing Overhead in Dispatch Operations: Cross-architecture Observatory

• URL: http://arxiv.org/abs/2605.20982v1
• Date: Wed, 20 May 2026 10:14:00 GMT
• Title: Diagnosing Overhead in Dispatch Operations: Cross-architecture Observatory
• Abstract summary: AlltoAll dispatch is the dominant bottleneck of MoE expert parallelism.<n>We introduce DODOCO to test two assumptions about the workload.<n> scaling EP changes the per-expert max/mean token ratio by at most 5% within every architecture's measurable range.
• Score: 1.081571058570587
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AlltoAll dispatch is the dominant bottleneck of MoE expert parallelism, and the interconnect community has responded with four families of mitigations: predictive sample placement, adaptive expert relayout, hierarchical collectives, and EP-aware topology. All four rest on two assumptions about the workload. The first is that routing imbalance is correctable by the system layer. The second is that the mock-token benchmarks evaluating them faithfully represent production routing. We introduce DODOCO to test both assumptions. We instrument five MoE checkpoints spanning five sequence-mixer designs (DeepSeek-V2-Lite MLA, DeepSeek-MoE-16B MHA, Qwen3-30B GQA, Nemotron-30B Mamba-2, Qwen3.5-35B GDN) under a 5 by 6 grid of data conditions plus a matched EP scan from 4 to 32 ranks on H100s; both assumptions fail. Scaling EP changes the per-expert max/mean token ratio by at most 5% within every architecture's measurable range: the straggler is intrinsic to the routing decision the model makes, not to how its experts land on ranks. Mock tokens overestimate routing Gini by up to a factor of 2.35 and fabricate a batch-size scaling trend that vanishes the moment real text replaces random IDs. A third pattern, unexpected, emerges from the same matrix: the five architectures cleave into two stable bands. MHA and Mamba-2 (data-resilient) drop to Gini 0.105 and 0.150 on wikitext. MLA and GDN (persistently concentrated) stay above 0.24 on every real-text condition and reach 0.29 to 0.38 on mock. GQA is the intermediate case. These bands, not the EP degree or the mock-data profile, are the right workload input to AlltoAll-aware interconnect and dispatch design.

Related papers

• On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability [57.03393882933515]
  We describe the architecture and ablations of Qwen3.8-Flash-Next, a sparse mixture-of-experts model with 125B parameters, 6B activated per token, and 51B parameters of n-gram embedding tables held off the accelerator.<n>On fourteen pre-training benchmarks the model leads the 397B-A17B predecessor on eight and trails it on the rest by at most 2.6 points, at 1/3 the activated parameters, 1/3 the training tokens, and roughly 1/9 the training FLOPs.
  arXiv  Detail & Related papers  (2026-08-31T06:35:07Z)
• Architecture-Dependent Causal Transfer of Activation States Across Large Language Models [51.56484100374058]
  Internal language activation states can be transferred causally between different large language models.<n>Injecting projected activations into a target model during generation produces a statistically significant, preregistered causal effect.<n>We conclude that end-to-end activation-state transfer between LLMs, as currently implemented, is architecture-dependent rather than universal.
  arXiv  Detail & Related papers  (2026-08-17T09:53:27Z)
• VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct [71.22358682581215]
  Scaling reinforcement learning for visual mathematical reasoning requires more than generating harder questions.<n>We instantiate this as VeriEvol, an iterative framework with two components.<n>On a five-benchmark visual-math suite, scaling evolved SFT data from 10K to 250K samples raises the mean accuracy from 35.42 to 54.73.
  arXiv  Detail & Related papers  (2026-06-22T16:17:30Z)
• Task Structure Reverses Layerwise State Encoding in Sequence Models [8.403971471573607]
  We find that the same architecture reverses this profile when the task changes.<n>In fine-tuned Mamba-130M and Pythia-160M, Parity is concentrated late in Mamba and the recurrent baselines and built gradually by Transformer.<n>The same flip appears in fine-tuned Mamba-130M and Pythia-160M, and the Pythia Dyck bottleneck persists at 410M.
  arXiv  Detail & Related papers  (2026-05-30T23:26:29Z)
• Convergence Theory for Iterative LLM-Based Neural Architecture Search: A Parametric Cross-Entropy Framework with Closed-Form Proxy Reliability [48.83701310501069]
  Large language models (LLMs) are increasingly used as generators in iterative neural architecture search (NAS)<n>We model iterative LLM-NAS as a parametric Cross-Entropy (CE) method over executable programs.<n>We prove six results: (1) iterative LLM fine-tuning on elite architectures is equivalent to the CE update restricted to the LLM family; (2) expected architecture quality is monotonically non-decreasing across cycles; and (3) elite-set probability converges to a fixed point at a geometric rate.
  arXiv  Detail & Related papers  (2026-05-28T15:45:19Z)
• Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction [51.56484100374058]
  Text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary.<n>On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834 across three architectures.<n>On RoBERTa-base, raw projection exceeds fine-tuning; on RoBERTa-base, full fine-tuning reduces discrimination below raw on both fluent-formal populations tested.
  arXiv  Detail & Related papers  (2026-05-20T19:08:38Z)
• Fidelity Probes for Specification--Code Alignment [7.754687669049819]
  We introduce fidelity probes: natural-dependence questions generated from a reference artifact with code-derived ground-truth answers.<n>The fidelity probes decompose into contradiction and coverage-gap rates that drive targeted spec edits to convergence.<n>On a 15-program, roughly 12k-line benchmark, we raise frozen-test specification fidelity from 0.63 to 0.94 over eight iterations.
  arXiv  Detail & Related papers  (2026-05-17T04:05:54Z)
• MolmoAct2: Action Reasoning Models for Real-world Deployment [67.6315757474802]
  MolmoAct2 is a fully open action reasoning model built for practical deployment.<n>We introduce MolmoER, a VLM backbone specialized for spatial and embodied reasoning.<n>We release three new datasets spanning low-to-medium cost platforms.
  arXiv  Detail & Related papers  (2026-05-04T17:51:21Z)
• HubRouter: A Pluggable Sub-Quadratic Routing Primitive for Hybrid Sequence Models [0.0]
  We introduce Hub Code, a pluggable module that replaces O(n2) attention layers with O(nM) hub-mediated routing.<n>We demonstrate it in two from-scratch architectures: a Jamba-style hybrid and a 12-layer Transformer.
  arXiv  Detail & Related papers  (2026-04-24T10:59:30Z)
• What Is the Minimum Architecture for Prolepsis? Early Irrevocable Commitment Across Tasks in Small Transformers [0.7310043452300737]
  We introduce textbfprolepsis: a transformer commits early, task-specific attention heads sustain the commitment, and no layer corrects it.<n>All experiments run on a single consumer GPU (16,GB VRAM)
  arXiv  Detail & Related papers  (2026-04-16T13:38:34Z)
• ClawArena: Benchmarking AI Agents in Evolving Information Environments [61.664633997138004]
  ClawArena is a benchmark for evaluating AI agents in evolving information environments.<n>Each scenario maintains a complete hidden ground truth while exposing the agent only to noisy, partial, and sometimes contradictory traces.<n> evaluation is organized around three coupled challenges: multi-source conflict reasoning, dynamic belief revision, and implicit personalization.
  arXiv  Detail & Related papers  (2026-04-05T17:55:23Z)
• ACAR: Adaptive Complexity Routing for Multi-Model Ensembles with Auditable Decision Traces [3.151184728006369]
  We present ACAR, a measurement framework for studying multi-model orchestration under auditable conditions.<n>ACAR uses self-consistency variance (sigma) computed from N=3 probe samples to route tasks across single-model, two-model, and three-model execution modes.<n>We evaluate ACAR on 1,510 tasks spanning four benchmarks, producing more than 7,550 auditable runs.
  arXiv  Detail & Related papers  (2026-02-06T23:27:17Z)
• What matters for Representation Alignment: Global Information or Spatial Structure? [64.67092609921816]
  Representation alignment (REPA) guides generative training by distilling representations from a strong, pretrained vision encoder to intermediate diffusion features.<n>We investigate a fundamental question: what aspect of the target representation matters for generation, its textitglobal revisionsemantic information.<n>We replace the standard projection layer in REPA with a simple convolution layer and introduce a spatial normalization layer for the external representation.
  arXiv  Detail & Related papers  (2025-12-11T16:39:53Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Deep Sparse Conformer for Speech Recognition [1.4649095013539173]
  Conformer has achieved impressive results in Automatic Speech Recognition. We adapt a sparse self-attention mechanism with $mathcalO(LtextlogL)$ in time complexity and memory usage. On the Japanese CSJ-500h dataset, this deep sparse Conformer achieves respectively CERs of 5.52%, 4.03% and 4.50%.
  arXiv  Detail & Related papers  (2022-09-01T06:56:11Z)
• Disentangle Your Dense Object Detector [82.22771433419727]
  Deep learning-based dense object detectors have achieved great success in the past few years and have been applied to numerous multimedia applications such as video understanding. However, the current training pipeline for dense detectors is compromised to lots of conjunctions that may not hold. We propose Disentangled Dense Object Detector (DDOD), in which simple and effective disentanglement mechanisms are designed and integrated into the current state-of-the-art detectors.
  arXiv  Detail & Related papers  (2021-07-07T00:52:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.