Dynamic applications, including optimal-transport Flow Matching, repeatedly solve related entropic optimal transport problems, yet conventional distributed Sinkhorn processes frames sequentially and synchronizes after every iteration. We present TemporalSinkhorn, a parallel-in-time executor that batches future candidates and their repairs without making output accuracy speculative. A centered, row-sharded certificate accepts only a deterministic safe prefix. The remaining candidates share packed Sinkhorn updates; an online projective forgetting rate places audit milestones, while a posteriori residual checks recover from every depth underestimate. Prediction can therefore change work placement but cannot authorize an inaccurate output. On 4 A100 GPUs, a 60-run, five-seed grid at n = 2048 shows that forgetting-guided milestones reduce wall time by 1.15x-1.47x relative to auditing every packed iteration in five statistically resolved regime cells. Against a sequential soft c-transform warm start, temporal execution is 1.42x-3.55x faster across six synthetic streams, with zero marginal-tolerance violations. On Flow Matching minibatch streams, temporal execution is 3.054x-3.632x faster than sequential carry at n = 2048, with no tolerance violations. A separate fixed-kernel test on an RTX 4060 Laptop GPU gives a 4.315x geometric-mean speedup. These are complementary deployment studies rather than a controlled hardware comparison. End-to-end Flow Matching integration, optimized-solver comparisons, and multi-node validation remain open.
The scaling of Large Language Models (LLMs) has driven significant performance gains but created substantial challenges in inference efficiency. While Mixture of Experts (MoEs) architectures address this by decoupling model size from inference cost, training MoEs from scratch is often unstable and compute intensive. Conversion of pre-trained dense models into sparse MoEs has emerged as an alternative solution; however, existing methods typically rely on heuristic neuron clustering or random splitting to partition the Feed-Forward Network (FFN) into experts. In this work, we propose DOT-MoE, a novel framework that formulates the decomposition of dense layers as a Differentiable Optimal Transport (DOT) problem. Instead of static heuristics, we model neuron assignment as a balanced transport problem, utilizing differentiable Sinkhorn-Knopp iterations to enforce strict expert capacity constraints. Furthermore, we utilize Straight-Through Estimators (STE) to jointly learn the discrete neuron-to-expert assignment and the token-to-expert routing policy end-to-end. Extensive experiments across multiple architectures and benchmarks demonstrate that DOT-MoE significantly outperforms structured pruning, heuristic clustering, and random-split baselines, retaining 90% of the original dense model's performance while reducing active parameters by 50%.
Speculative decoding accelerates Large Language Models via draft-then-verify, where verification can be framed as an Optimal Transport (OT) problem. Existing approaches typically handle multi-draft and multi-step aspects in isolation, applying either flat OT to single-step drafts or per-token rejection sampling to tree-structured candidates. This separation leaves the joint regime (where multi-step dependencies meet multi-draft branching) poorly optimized, as local verification rules fail to exploit the coupling between horizontal and vertical dimensions of candidate trees. In this paper, we propose a unified perspective that casts tree-based verification as a conditional OT problem. Our key insight is that vertical dependencies can be abstracted through prefix acceptance probabilities, which act as dynamic scaling factors to actively guide horizontal draft selection. Based on this principle, we introduce UniVer, a verification algorithm that jointly optimizes across tree levels by composing local optimal transport plans under prefix constraints. We prove that UniVer remains lossless and achieves the optimal acceptance rate under the proposed conditional framework. Extensive experiments across different tasks and models demonstrate that UniVer improves acceptance length by 4.2% to 8.5% over standard recursive rejection sampling without replacement, while maintaining exact distributional alignment with the target model.