DrainSinkhorn is a verifier‑gated active‑packing layer that improves batched entropic optimal transport (EOT) by eliminating finished problems from subsequent Sinkhorn updates. It combines candidate‑axis packing, a one‑sided screen, verifier‑gated retirement, and physical compaction, while keeping the EOT objective, per‑instance map, and stopping rule unchanged. The method achieves state‑of‑the‑art execution speedups—up to 4.11× faster on MetroPT‑3 and 3.80× on ImageNet‑32 feature couplings—across multiple backends and tolerance settings. whyItMatters":"The technique delivers significant runtime reductions for heterogeneous batched‑EOT workloads, enabling faster and more efficient optimal transport computations in practical machine‑learning pipelines."
arXiv:2607. 24741v1 Announce Type: cross Abstract: 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.
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.
arXiv:2606. 19989v1 Announce Type: cross Abstract: Modern LLM training breaks a core assumption behind offline batch samplers: the true training cost of a sample is only observable after preprocessing, augmentation, templating, tokenization, and multimodal visual-token expansion.
The paper investigates whether training Mixture-of-Experts (MoE) routers can improve memory‑bandwidth locality on consumer GPUs. Using a new zero‑surgery telemetry tool, the authors measure that a large Qwen3‑235B model is bottlenecked by disk‑based expert access, and that an LRU cache can serve a majority of requests. They pre‑register experiments training 137 M‑parameter MoE models with locality‑aware losses, finding that while cache misses can drop up to 60 % (99 % static‑pin hit rate), every configuration fails to meet a strict 1 % perplexity threshold, indicating a tight coupling between cache efficiency and model quality.
arXiv:2608. 13987v1 Announce Type: new Abstract: Nanbeige4.
Serving a 235B-parameter Mixture-of-Experts (MoE) model on a single 8 GB GPU is bottlenecked not by compute but by memory bandwidth: decode must stream each token's active experts from whichever tier holds them, and on consumer hardware most experts sit on an SSD far slower than RAM. We quantify this bandwidth wall on Qwen3-235B (Q4_K_M, 134 GB): measured decode is 0.
arXiv:2608. 03447v1 Announce Type: cross Abstract: Speculative decoding accelerates autoregressive generation by verifying a draft block with a target model in parallel.
arXiv:2607. 02043v1 Announce Type: cross Abstract: Disaggregated LLM serving runs prefill and decode on separate GPU pools to keep the two phases from interfering.
arXiv:2607. 23264v1 Announce Type: cross Abstract: Fine-grained, device-initiated communication lets persistent GPU kernels in distributed diffusion transformer (DiT) inference issue remote stores and overlap data movement with Tensor Core computation.
arXiv:2607. 24665v1 Announce Type: cross Abstract: Modern large language models scale successfully by pairing capacity growth with efficiency, keeping per-token and deployment costs under control as capacity grows.
arXiv:2606. 19004v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training of Diffusion Transformers (DiTs) is prohibitively expensive, requiring thousands of high-end GPUs.
arXiv:2606. 14598v1 Announce Type: new Abstract: Post-training INT8 (W8A8) quantization of diffusion transformers is widely deployed as a speed optimization, yet on consumer Ampere GPUs it is frequently slower than the FP8 and NF4 alternatives it is meant to beat.