CORTEXA
← Browse
arxivcs.DCcs.LG2026-07-08

CTA-Pipelining: A Latency-Oriented Spatial Scaling Method for Multi-GPU Systems

Tingkai Liu, Muralidhar Andoorveedu, Sanjoy Das, Sanjay Patel, Volodymyr Kindratenko

The evolution of compute infrastructure has transformed multi-GPU systems into tightly integrated shared-memory structures. However, current software still mostly treats these coherent interconnects simply as high-speed networks. Simultaneously, the demand for serving Large Language Models under latency constraints has shifted GPU workload optimization from being throughput-driven to latency-bound, necessitating latency-oriented scaling methods beyond Tensor Parallelism (TP). Thus, we introduce CTA-pipelining, an execution paradigm designed to exploit shared-memory multi-GPU systems. As a latency-oriented spatial scaling technique, CTA-pipelining leverages dependencies at the Cooperative Thread Array level, enabling concurrent execution of dependent kernels across GPUs. We demonstrate its capability using CUTLASS, cuBLAS, and NCCL libraries on 8-GPU H200 and B200 systems. Results show on 2-layer GEMM, representing the MLP operation, CTA-pipelining reduces latency by up to 31.8% compared to micro-batching, and 29.6% compared to TP. It can also be combined with TP as an orthogonal scaling dimension to further push the latency boundary.

View free PDFSource page

Related papers

arxivcs.LGcs.DC2026-07-09Cited by 2

Collate: Collaborative Neural Network Learning for Latency-Critical Edge Systems

Shuo Huai, Di Liu, Hao Kong, Xiangzhong Luo, Weichen Liu, Ravi Subramaniam, et al.

Federated Learning (FL) empowers multiple clients to collaboratively learn a model, enlarging the training data of each client for high accuracy while protecting data privacy. However, when deploying FL in real-time edge systems, the heterogeneity of devices among systems has a s…

View free PDFSource page
arxivcs.LGcs.AIcs.DCcs.PF2026-07-06

Adaptive Inference Batching using Policy Gradients

Ruslan Sharifullin

Inference serving systems must balance throughput and latency under bursty, heterogeneous workloads, yet the industry standard remains static batching policies that require manual tuning and cannot adapt to shifting traffic. We investigate whether reinforcement learning (RL) can…

View free PDFSource page
arxivcs.DCcs.LG2026-07-13

FlashDiff: Efficient Regional Execution and Scheduling for Diffusion Model Serving

Yaqi Qiao, Ping He, Songrun Xie, Ayush Barik, Chensong Zhang, Zhengzhong Tu, et al.

Diffusion models have become the central backbone for modern image, video, and audio generation, but their efficient service remains a challenge. Unlike autoregressive decoding, diffusion inference repeatedly updates high-dimensional spatial or temporal latents over many denoisin…

View free PDFSource page
arxivcs.LGcs.DCq-bio.QM2026-07-03

Design-CP: Context Parallelism for Design of Protein Nanoparticles

Lorenzo Tarricone, Helen E. Eisenach, Aiko Muraishi, Charlotte M. Deane

Many all-atom generative protein models can in principle design large multimeric complexes by jointly modelling all chains, but their quadratic token- and atom-pair representations quickly exceed single-GPU memory as the number of chains and residues modelled grows. We introduce…

View free PDFSource page
arxivcs.LGcs.DC2026-07-02

SCAPE: Accurate and Efficient LLM Training with Extreme Sparse Communication

Mingkai Zheng, Junlin Chen, Haotian Xie, Zhao Zhang

Communication increasingly dominates the cost of Large Language Model (LLM) pre-training, especially under data-parallel and sharded training schemes, where gradient synchronization and parameter reconstruction overhead increase with model size and system scale. Existing communic…

View free PDFSource page
arxivcs.LGcs.AIcs.DCcs.PF2026-07-16

An Auto-Scaling Approach for Serverless Environments Based on a Multi-Expert Consensus Mechanism

Mobina Kashaniyan, Mehrdad Ashtiani, Amirhossein Ghassemi

Serverless computing provides automatic resource management and pay-per-use execution, but effective autoscaling remains challenging because of dynamic workloads, cold-start latency, and dependencies among functions. We present a dependency-aware autoscaling framework that integr…

View free PDFSource page