Multi-Gpu Systems

Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

8 new papers

A weekly snapshot of new work published in Multi-Gpu Systems.

Period ending 2026-09-14

3 new papers

A weekly snapshot of new work published in Multi-Gpu Systems.

Period ending 2026-09-07

10 new papers

A weekly snapshot of new work published in Multi-Gpu Systems.

Inside this field

Focused directions

274 papers

Latest in Multi-Gpu Systems

Browse all topics →
CardsList

  1. Accelerating the Mitigation of LLM Inference Nondeterminism Across GPU Architectures

    Sep 22, 2026Liam Cooper, Shinnung Jeong, Hyeran Jeon +2LLM Inference EfficiencyMulti-Gpu Systems

  2. Task-Oriented Active Learning of Residual Dynamics for Model Predictive Path Integral Control

    Sep 16, 2026Nobuaki Aoki, Hojin Lee, Stefan Sosnowski +1Model Predictive Path IntegralActive Learning

  3. Ask the Tool, Don't Guess: Agent Tool Calls Hold Their Progress, and the Serving System Should Read It

    Sep 16, 2026Yipeng Liu, Yingqiang Zhang, Feifei Li +1Multi-Turn Tool-Use AgentCall

  4. Layer-wise Curriculum Learning for Efficient LLM Compression

    Sep 16, 2026Donggeon Lee, Dooyeon Na, Seungmin Oh +1Large Language Model CompressionGraphics Processing Unit Memory

  5. SEA-LION-v4.8: A Technical Report

    Sep 16, 2026Ahmed Mohammad Dabeer, Ahn Jeongmi, Anocha Sutaveephamochanon +45PhilippinesTechnical Report

  6. Breaking the 1.58-bit Barrier for Ternary LLMs

    Sep 14, 2026Evangelos Georganas, Alexander Heinecke, Pradeep DubeyLarge Language Model QuantizationLarge Models

  7. Shared KV Caching for Replicated 27B Inference: Correctness Failures and Performance Boundaries

    Sep 14, 2026Frank LiKv-Cache BlocksCache

  8. Rethinking Heterogeneous System Disaggregation for Subquadratic Attention

    Sep 14, 2026Arya Tschand, Yaosheng Fu, Vikram Sharma Mailthody +6Quadratic AttentionGraphics Processing Unit Memory

  9. Dissecting GPU Utilization for LLM Inference on Nvidia Hopper

    Sep 14, 2026Mohammad Siavashi, Gerald Q. Maguire Jr., Dejan Kostic +1Nvidia NemotronLLM Inference Efficiency

  10. Building py-kvcache: A Performance Characterization of External KV Caching for vLLM with NVMe SSDs

    Sep 11, 2026Joseph Kanichai, Tiziano De Matteis, Animesh TrivediKv-Cache BlocksKey-Value Cache

  11. Numbat: Building and Verifying a Self-Contained Machine-Learning Stack

    Sep 9, 2026Thang Tran, Lan DangMachine LearningModel Training

  12. GPU-Enabled Large-Scale Optimization Using Randomized Linear Algebra

    Sep 8, 2026Pratik Rathore, Zachary Frangella, Parth Nobel +2Multi-Gpu SystemsRiemannian Optimization

  13. Jacap: Robust KV Cache Eviction via Jacobian-Based Nonlinear Information Capacity Preservation

    Sep 8, 2026Jiaming Yang, Chenwei Tang, Liangli Zhen +2Key-Value Cache EvictionQuadratic Attention

  14. MetaKV: Adaptive KV Cache Compression for Constrained LLM Inference

    Sep 7, 2026Michael Wang, Keith Li, Roozbeh BostandoostKey-Value Cache CompressionLLM Inference Efficiency

  15. Scalability Analysis of Distributed Kolmogorov-Arnold Network Training on High-Performance Computing Systems

    Sep 7, 2026Guangneng Chen, David Garcia Selfa, Pablo Quesada BarriusoKolmogorov-Arnold NetworksHigh-Performance Computing

  16. GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning Serving

    Sep 3, 2026Qiankun Ma, Yanjiang Zhou, Zinan Xiong +5Graphics Processing Unit MemoryLarge Language Model Reasoning

  17. SGD-KV: Summarization Guided KV Cache Compression

    Sep 3, 2026Zeyu Liu, Woomin Song, Xuandi Fu +5Key-Value Cache CompressionEfficient Long-Context Inference

  18. LeanStream: A Speculate-and-Refine Streaming Framework for Efficient on-Device LLM Inference

    Sep 2, 2026Renyuan Liu, Yuyang Leng, Kaiyan Liu +7LLM Inference EfficiencySingle Graphics Processing Unit

  19. Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation

    Sep 2, 2026Zhiwei Zhang, Zechen Sun, Fei Zhao +6On-Policy DistillationTeacher

  20. HeadWiseKV: Budgeted Per-Head Cache Residency for Hybrid Long-Context Language Models

    Sep 2, 2026Renjie Xie, Juncheng Yang, Aoting Hu +4Efficient Long-Context InferenceKey-Value Cache

  21. MeshSplatBench: A Unified Benchmark for Triangle-Based Neural Rendering

    Sep 1, 2026Kaixuan Zhang, Minxian Li, Mingwu Ren +1Neural RenderingRasterization

  22. Workload Identification with Physical Side Channels for AI Governance

    Aug 31, 2026Simone Gargiulo, Gabriel KulpInference WorkloadsWorkload

  23. Faster Than Flash: Exploiting Attention Sparsity for Efficient Long-Context Decoding

    Aug 31, 2026Zhigeng Liu, Zhiyuan Ning, Ruixiao Li +5Efficient Long-Context InferenceDynamic Sparse Attention

  24. Deploying DeepSeek 175B Locally on a Single Consumer-Grade RTX 4060 Laptop with 32GB RAM for 200k-Scale Protein-Ligand Virtual Screening

    Aug 31, 2026Rui Xiao, Yili XuStructure-Based Drug DesignDeepseek

  25. Amortized Anchor Refinement for Deployable Continuous-Time 4D Gaussian Reconstruction

    Aug 31, 2026Jingong Chen, Qingwen Zhang, Sanghyeon Jun +34D ReconstructionDiffusion Refinement

  26. Budget-Aware Compression Pipeline for Single-GPU LLM Inference: Methods, Trade-offs, and Coupling Effects

    Aug 30, 2026Hongyu Yu, Yifei ShenLarge Language Model CompressionLLM Inference Efficiency

  27. Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090

    Aug 27, 2026Kairong Luo, Jiarui Cui, Yaorui Yin +8Large Language Model PretrainingQwen3

  28. PAGE: Partition-Aware Gated KV-Cache Eviction

    Aug 26, 2026Pankaj Kumar, Subhankar MishraKey-Value Cache EvictionPer-Token Latency

  29. CRESSim-Neo: A Batched GPU Simulation Engine for Surgical Robotics and Robot Learning

    Aug 25, 2026Yafei Ou, Ahnaf Naheen, Tleukhan Mussin +3Robot-Assisted Minimally Invasive SurgeryPhysics Simulation

  30. vToken: Token-Level Virtualization for Reclaimable KV Caches

    Aug 13, 2026Yuanhang Gao, Xiangrui Yang, Yuanfeng Chen +4Key-Value CacheGraphics Processing Unit Memory

  31. TEMPO: Makespan-Aware Expert-Parallel Load Balancing Across Memory- and Compute-Bound Regimes

    Aug 13, 2026Jie Li, Chenxin Jia, Jinliang Shen +5Load BalancingMulti-Gpu Systems

  32. DMDIntel: Interpreting Large Language Models via Dynamic Mode Decomposition

    Aug 13, 2026Amogh Joshi, Animesh Mukherjee, Sergey UtyuzhnikovVisual AttributionNvidia Nemotron

  33. CAKE: Compiler-Agent Co-Design for Frontier Kernel Evolution

    Aug 12, 2026Zihao Ye, Yingyi Huang, Hongyi Jin +11Graphics Processing Unit KernelsSingle Graphics Processing Unit

  34. Ready Cohorts: Bounding GPU Opportunity and Avoiding Host Round Trips in LLM-Agent Control

    Aug 12, 2026Josef Liyanjun ChenMulti-Gpu SystemsConsumer Graphics Processing Units

  35. LazyTrain: Limited-resource Allocation toward Zero-waste Yield Optimization in Large Language Model Training

    Aug 12, 2026Xiaojun Wu, Cehao Yang, Honghao Liu +5Large ModelsGraphics Processing Unit Memory

  36. CARB: A Characterization-Guided Framework for CNN Inference Cost Prediction and Deployment Screening

    Aug 11, 2026Linh Nguyen, Zhixin PanGraph Neural Network InferenceInference Workloads

  37. Hand-Written PTX Tensor-Core GEMM Kernels: A Multi-Precision Study on NVIDIA L4

    Aug 10, 2026Matt J. Borowski, Blazej OsinskiTensor ProgramsGraphics Processing Unit Kernels

  38. Governing the KV Cache: Preventing Timing Side-Channel Leakage in Multi-Tenant LLM Inference

    Aug 10, 2026Tejasvi C. AddagadaKv-Cache BlocksKey-Value Cache

  39. SwiftQK: Fast and Communication-Efficient Tensor Parallelism for Query-Key Normalization

    Aug 10, 2026Gyudong Kim, Wonjun Han, Young Geun KimTensor ProgramsQuadratic Attention

  40. Gradient Under Microscope: Benchmarking Resource Utilization of Memory-Efficient Gradient Computation Methods

    Aug 9, 2026Sarthak Mahapatra, Zihan Zhou, Khatoon Khedri +2Graphics Processing Unit MemorySingle Graphics Processing Unit

  41. RippleKV: Cross-Layer KV Cache Allocation via Perturbation Propagation

    Aug 9, 2026Dongjie Xu, Kai Qian, Julius +6Key-Value Cache CompressionCache

  42. What Irregularity Costs: CUDA C++, Rust, and Triton on a Hash-Blocked GPU Workload

    Aug 8, 2026Petr KorolevCudaSingle Graphics Processing Unit

  43. SPECTRA: Pushing the KV Cache Beyond the 2-Bit Cliff via Spectral Transform Coding

    Aug 8, 2026Jiamu Zhang, Liang Wu, Kelly Wan +2Key-Value CacheCache

  44. LGNNIC: Acceleration of Large-Scale GNN Training using SmartNICs

    Aug 7, 2026Liad Gerstman, Aditya Dhakal, Dejan Milojicic +1Graph Neural NetworksMulti-Gpu Systems

  45. Dual-Node NVIDIA DGX Spark over Tailscale: A Remote-Access Testbed for Distributed LLM Training and Cyber-Threat-Intelligence Fine-Tuning

    Aug 7, 2026Vasanth IyerNvidia NemotronAccelerator

  46. Every Cache Entry Earns Its Place: Global Allocation of Resolution and Coverage for KV Cache Compression

    Aug 7, 2026Haolin Tian, Yuzhe Liu, Tonghan WangKey-Value Cache CompressionCache

  47. Multi-Level Modeling of Large Language Model Inference Latency and Energy via Hybrid Analytical--Machine-Learning Predictors

    Aug 7, 2026Saeid Shokoufa, Mohammad Erfan Sadeghi, Mehdi Kamal +1LLM Inference EfficiencyNvidia Nemotron

  48. Density-Functional Excited-State Gradients and Nonadiabatic Couplings on a Consumer GPU from a Contraction-DAG

    Aug 6, 2026Rubén Darío GuerreroDensity Functional TheoryContraction

  49. Operating Multi-Node Full Fine-Tuning on NVIDIA B300: A Field Report on Telemetry-Based Triage, Negative Results, and Operational Hardening

    Aug 6, 2026Seon Ho Kim, Ui Jeong Jeon, Su Hyeon Kim +1Nvidia NemotronAccelerator

  50. Energy- and Memory-Efficient PEFT Methods for Personalized On-Device SLMs on Consumer GPUs

    Aug 5, 2026Kuanysh Akhmetzhanov, Jurn-Gyu ParkParameter-Efficient Fine-TuningFinetuning

  51. LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic Manipulation

    Aug 4, 2026Fan Yang, Yuting Su, Xiaobo Wang +7Efficient World-Action ModelLatent World Models

  52. Accelerating Dynamic Graph Clustering on GPU Architectures with cuGraph

    Aug 4, 2026Nelson Aloysio Reis de Almeida Passos, Emanuele Carlini, Salvatore TraniGraph RepresentationsNvidia Nemotron

  53. Pin Once, Swap Light: Subspace-Aligned Centroid-Residual Training for Efficient Ultra-LoRA Serving

    Aug 4, 2026Xiang Li, Pengcheng Wang, Huazheng Wang +1Low-Rank Adaptation AdaptersLarge Language Model Serving

  54. Energy-Efficient LLM Serving via Disaggregated Attention--FFN and Flexible Frequency Scaling

    Aug 3, 2026Cunchen Hu, Liangliang Xu, Tian Liu +9Single Graphics Processing UnitWell-Tuned Static Batching Policy

  55. Gram-Space: Structure-Preserving Codebook Compression for Memory-Efficient Neuro-Symbolic AI

    Aug 2, 2026Weilun Wang, Wantong LiNeuro-Symbolic FrameworkCodebooks

  56. HetRoute Heterogeneous and Cost-aware Collaborative Routing Framework for Distributed Edge MoE Inference

    Aug 1, 2026Xin Yuan, Ning Li, Wenchao Xu +2Mixture-Of-Expert InferenceHeterogeneous Edge Devices

  57. LinearKV: One Cached State Suffices for Position-Independent Caching in Hybrid LLMs

    Jul 31, 2026Yirui Liu, Ruoling Qi, Longwen Wang +5Quadratic AttentionCache

  58. Back from the Future: Key-Value Cache Management by Counter-Causal Surprise

    Jul 30, 2026Stephen Gould, Anton van den HengelKey-Value CacheCache

  59. TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

    Jul 29, 2026Hengyi Xie, Chenfei Yao, Xianjin Wu +7Pretrained Vision-Language-ActionLarge Vision Language Models

  60. Device-First Feedback: Toward Mobile-Native LLM-Driven Neural Architecture Search

    Jul 29, 2026Saif U Din, Muhammad Ahsan Hussain, Radu Timofte +1Mobilenetv2Neural Architecture Search