{"total":33,"rows":[{"id":"2410.18038","title":"POD-Attention: Unlocking Full Prefill-Decode Overlap for Faster LLM Inference","created":"2024-10-23","cited_by_count":47,"area":null},{"id":"2509.16293","title":"Robust LLM Training Infrastructure at ByteDance","created":"2025-09-19","cited_by_count":16,"area":null},{"id":"2505.11329","title":"TokenWeave: Efficient Compute-Communication Overlap for Distributed LLM Inference","created":"2025-05-16","cited_by_count":14,"area":null},{"id":"2504.19519","title":"Efficient and Adaptable Overlapping for Computation and Communication via Signaling and Reordering","created":"2025-04-28","cited_by_count":10,"area":null},{"id":"2409.15241","title":"Domino: Eliminating Communication in LLM Training via Generic Tensor Slicing and Overlapping","created":"2024-09-23","cited_by_count":9,"area":null},{"id":"2501.06589","title":"Ladder-residual: parallelism-aware architecture for accelerating large model inference with communication overlapping","created":"2025-01-11","cited_by_count":9,"area":null},{"id":"2510.20171","title":"Collective Communication for 100k+ GPUs","created":"2025-10-23","cited_by_count":4,"area":null},{"id":"2409.11155","title":"ISO: Overlap of Computation and Communication within Seqenence For LLM Inference","created":"2024-09-04","cited_by_count":3,"area":null},{"id":"2503.04983","title":"Leveraging Large Language Models For Scalable Vector Graphics Processing: A Review","created":"2025-03-06","cited_by_count":3,"area":null},{"id":"2505.15765","title":"Constructing a 3D Scene from a Single Image","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2512.08905","title":"Self-Evolving 3D Scene Generation from a Single Image","created":"2025-12-09","cited_by_count":3,"area":null},{"id":"2601.17654","title":"Kareus: Joint Reduction of Dynamic and Static Energy in Large Model Training","created":"2026-01-25","cited_by_count":3,"area":null},{"id":"2604.17172","title":"UCCL-Zip: Lossless Compression Supercharged GPU Communication","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2504.04279","title":"Could AI Trace and Explain the Origins of AI-Generated Images and Text?","created":"2025-04-05","cited_by_count":1,"area":null},{"id":"2512.10236","title":"Design Space Exploration of DMA based Finer-Grain Compute Communication Overlap","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2601.20461","title":"Exploiting the Final Component of Generator Architectures for AI-Generated Image Detection","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2602.07306","title":"Parallel Track Transformers: Enabling Fast GPU Inference with Reduced Synchronization","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2605.17879","title":"Guard: Scalable Straggler Detection and Node Health Management for Large-Scale Training","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2410.07531","title":"Reducing the Cost of Dropout in Flash-Attention by Hiding RNG with GEMM","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2412.13614","title":"Reverse Region-to-Entity Annotation for Pixel-Level Visual Entity Linking","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2509.16702","title":"Animalbooth: multimodal feature enhancement for animal subject personalization","created":"2025-09-20","cited_by_count":0,"area":null},{"id":"2511.12500","title":"Iris: First-Class Multi-GPU Programming Experience in Triton","created":"2025-11-16","cited_by_count":0,"area":null},{"id":"2604.24013","title":"CommFuse: Hiding Tail Latency via Communication Decomposition and Fusion for Distributed LLM Training","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.21603","title":"DynaFlow: Transparent and Flexible Intra-Device Parallelism via Programmable Operator Scheduling","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.09200","title":"Resource-aware Computation-Communication Overlap for multi-GPU ML Workloads","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.11169","title":"Piper: A Programmable Distributed Training System","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.07862","title":"CTA-Pipelining: A Latency-Oriented Spatial Scaling Method for Multi-GPU Systems","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.09160","title":"SwiftQK: Fast and Communication-Efficient Tensor Parallelism for Query-Key Normalization","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.13585","title":"mKernel: Fast Multi-GPU, Multi-Node Fused Kernels","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.13846","title":"Affinity-Aware Sharding for Delayed Tensor Parallelism","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2610.14277","title":"Echo: Error-Compensated 4-Bit Tensor-Parallel Communication for LLM Training and Inference","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14935","title":"BSIPipe: Bidirectional Sequence-Level Interleaved Pipeline Parallelism for Long-Sequence Large Language Model Training","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.17901","title":"FlashMask-3: Efficient and Expressive Mask-Aware Distributed Attention","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}