arXiv AI July 28, 2026 By Jianwen Xian, Zhiyuan Xu, Yuchen Li, Ziliang Lai, Kang He, Zhen Huang, Aichen Feng, Jinyan Chen, Yilin Zhang, Qinqin Chen, Chengru Song

X-Stage: An Overlooked Pipeline Stage for Communication-Computation Overlap in DiT Inference

Read the original on arXiv AI →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Sep 15

X-Stage: Modeling Post-Issue Backpressure in GPU Communication--Computation Fusion

arXiv:2607.23264v2 Announce Type: replace-cross Abstract: Fine-grained, device-initiated communication allows fused GPU kernels to issue remote stores directly from their compute pipelines, a pattern...

By Jianwen Xian, Zhiyuan Xu, Yuchen Li, Ziliang Lai, Kang He, Zhen Huang, Aichen Feng, Jinyan Chen, Yilin Zhang, Qinqin Chen, Julien Lai, Chengru Song

arXiv AI

Jul 23

Fine-grained Computation-Communication Overlap via Tile-level Signaling and Scheduling for Mixture-of-Experts

arXiv:2607. 19539v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures increase model capacity without proportionally increasing computation cost and have become a key building block for scaling large language models (LLMs) to trillion-parameter regimes.

By Minyu Cui, Anna Wingkvist, Morgan Ericsson

llms benchmarks

arXiv AI

Jun 10

Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid Design

arXiv:2606. 10493v1 Announce Type: cross Abstract: Local deployment of large Mixture-of-Experts (MoE) models falls short of the service quality achieved in cloud-scale environments, even under low-concurrency workloads.

By Wenxin Wang, Yule Hou, Yu Ji, Peng Qu, Youhui Zhang

efficiency

arXiv Machine Learning

Jul 3

GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving

arXiv:2606. 13501v2 Announce Type: replace-cross Abstract: Diffusion Transformers (DiTs) have become the dominant architecture for image and video generation, creating growing demand for efficient DiT serving.

By Xinwei Qiang, Yifan Hu, Shixuan Sun, Jing Yang, Han Zhao, Chen Chen, Yu Feng, Jingwen Leng, Minyi Guo

llms diffusion efficiency

arXiv Machine Learning

Jul 28

FusionML: Prefill, Not Decode - Mechanism and Boundaries of CPU+GPU Co-Execution on Unified-Memory Apple Silicon

arXiv:2607. 22785v1 Announce Type: cross Abstract: Apple-Silicon SoCs share CPU, GPU, and Neural Engine over one unified memory system, raising the question of whether transformer inference can be accelerated by splitting single operators across units.

By Om Mohite

llms efficiency

arXiv AI

Jul 3

Towards Load-Aware Prefill Deflection for Disaggregated LLM Serving

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.

By Shrikara Arun, Anjaly Parayil, Srikant Bharadwaj, Renee St. Amant, Victor R\"uhle

llms benchmarks

One email a morning, machine-written

Related stories

X-Stage: Modeling Post-Issue Backpressure in GPU Communication--Computation Fusion

Fine-grained Computation-Communication Overlap via Tile-level Signaling and Scheduling for Mixture-of-Experts

Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid Design

GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving

FusionML: Prefill, Not Decode - Mechanism and Boundaries of CPU+GPU Co-Execution on Unified-Memory Apple Silicon

Towards Load-Aware Prefill Deflection for Disaggregated LLM Serving