ChunkFlow: Communication-Aware Chunked Prefetching for Layerwise Offloading in Distributed Diffusion Transformer Inference

• URL: http://arxiv.org/abs/2605.11335v1
• Date: Mon, 11 May 2026 23:41:16 GMT
• Title: ChunkFlow: Communication-Aware Chunked Prefetching for Layerwise Offloading in Distributed Diffusion Transformer Inference
• Abstract summary: ChunkFlow is a communication-aware, chunk-granular offloading runtime for GPU memory.<n>It delivers up to 1.28x step-time speedup over SGLang's existing layerwise offloading.<n>ChunkFlow exposes a tunable memory-latency tradeoff that recovers near-zero step-time overhead in the small-workload regime.
• Score: 13.062229091130115
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Layerwise offloading reduces the GPU memory footprint of large diffusion transformer (DiT) inference by prefetching upcoming layers from host memory, but its effectiveness hinges on hiding prefetch latency behind per-layer computation. This assumption breaks down when the per-GPU compute workload is small. Moreover, on PCIe-only nodes, prefetch and inter-GPU collective communications such as all-reduce and all-to-all contend on the shared PCIe path, exposing prefetch latency even when compute would otherwise hide it. We revisit layerwise offloading as a co-scheduling problem between prefetch and communication, guided by a first-order analytical model that predicts when prefetch can be hidden by computation. Building on this model, we design ChunkFlow, a communication-aware, chunk-granular offloading runtime that adaptively yields to collective communication and smoothly trades GPU memory for prefetch volume. On three representative diffusion transformers running on two H100 GPUs over PCIe with Ulysses sequence parallelism, ChunkFlow delivers up to 1.28x step-time speedup over SGLang's existing layerwise offloading, reduces peak GPU memory by up to 49% over the no-offload baseline at near-identical step time once the workload is large enough, and exposes a tunable memory-latency tradeoff that recovers near-zero step-time overhead in the small-workload regime.

Related papers

• Profiling-Driven Adaptive Distributed Transformer Inference on Embedded Edge Deployment [60.442064966340524]
  We present a prototype study on NVIDIA Jetson Orin Nano devices connected over WiFi.<n>Key finding is that the dominant bottleneck is not just network bandwidth but also the CPU- GPU staging during communication.<n>Experiments show that this strategy reduces latency by 65%-77% and energy consumption by 34%-52% relative to full-tensor exchange.
  arXiv  Detail & Related papers  (2026-05-25T10:39:28Z)
• Out of the Memory Barrier: A Highly Memory Efficient Training System for LLMs with Million-Token Contexts [68.79341332280062]
  Training Large Language Models (LLMs) on long contexts is severely constrained by prohibitive GPU memory overhead, not training time.<n>We introduce OOMB, a highly memory-efficient training system that directly confronts this barrier.<n>Our approach employs a chunk-recurrent training framework with on-the-fly activation recomputation, which maintains a constant activation memory footprint.
  arXiv  Detail & Related papers  (2026-02-02T13:52:40Z)
• Harvest: Opportunistic Peer-to-Peer GPU Caching for LLM Inference [0.0]
  Large Language Model (LLM) inference is increasingly constrained by GPU memory capacity rather than compute throughput.<n>We present Harvest, an opportunistic GPU cache management framework that exploits high-bandwidth peer-to-peer GPU interconnects.<n>We demonstrate significant throughput speedup of more than 2 times by using Harvest to accelerate the retrieval of two widely-used inference components.
  arXiv  Detail & Related papers  (2026-01-30T21:29:04Z)
• Nexus:Proactive Intra-GPU Disaggregation of Prefill and Decode in LLM Serving [4.309392302169281]
  Engine-level prefill-decode (PD) disaggregation avoids interference but incurs higher hardware and coordination overhead.<n>PD achieves up to 2.2x higher throughput, 20x lower TTFT, and 2.5x lower TBT than vLLM; outperforms SG by up to 2x; and matches or exceeds disaggregated vLLM.
  arXiv  Detail & Related papers  (2025-07-09T07:27:18Z)
• Minute-Long Videos with Dual Parallelisms [57.22737565366549]
  Diffusion Transformer (DiT)-based video diffusion models generate high-quality videos at scale but incur prohibitive processing latency and memory costs for long videos.<n>We propose a novel distributed inference strategy, termed DualParal.<n>Instead of generating an entire video on a single GPU, we parallelize both temporal frames and model layers across GPUs.
  arXiv  Detail & Related papers  (2025-05-27T11:55:22Z)
• HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading [79.38548165722229]
  HEADINFER offloads the KV cache to CPU RAM while avoiding the need to fully store the KV cache for any transformer layer on the GPU.<n>We demonstrate HEADINFER maintains computational efficiency while significantly reducing memory footprint.
  arXiv  Detail & Related papers  (2025-02-18T06:26:05Z)
• KVPR: Efficient LLM Inference with I/O-Aware KV Cache Partial Recomputation [7.204881999658682]
  Key-Value cache is used to store intermediate activations for large language models.<n>The memory required for the KV cache grows rapidly, often exceeding the capacity of GPU memory.<n>Existing methods attempt to address these issues by overlapping GPU computation with I/O or employing CPU-GPU heterogeneous execution.<n>We introduce KVPR, an efficient I/O-aware LLM inference method where the CPU first transfers a partial set of activations.<n> KVPR achieves up to 35.8% lower latency and 46.2% higher throughput during decoding compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-11-26T04:03:14Z)
• LSM-GNN: Large-scale Storage-based Multi-GPU GNN Training by Optimizing Data Transfer Scheme [12.64360444043247]
  Graph Neural Networks (GNNs) are widely used today in recommendation systems, fraud detection, and node/link classification tasks. To address limited memory capacities, traditional GNN training approaches use graph partitioning and sharding techniques. We propose Large-scale Storage-based Multi- GPU GNN framework (LSM-GNN) LSM-GNN incorporates a hybrid eviction policy that intelligently manages cache space by using both static and dynamic node information.
  arXiv  Detail & Related papers  (2024-07-21T20:41:39Z)
• Communication-Efficient Graph Neural Networks with Probabilistic Neighborhood Expansion Analysis and Caching [59.8522166385372]
  Training and inference with graph neural networks (GNNs) on massive graphs has been actively studied since the inception of GNNs. This paper is concerned with minibatch training and inference with GNNs that employ node-wise sampling in distributed settings. We present SALIENT++, which extends the prior state-of-the-art SALIENT system to work with partitioned feature data.
  arXiv  Detail & Related papers  (2023-05-04T21:04:01Z)
• Demand Layering for Real-Time DNN Inference with Minimized Memory Usage [2.5768647103950357]
  Deep neural network (DNN) model parameters are loaded into GPU memory before execution. We present Demand Layering, which exploits the layer-by-layer execution of DNNs. Our implementation shows a 96.5% memory reduction with just 14.8% delay overhead on average.
  arXiv  Detail & Related papers  (2022-10-08T13:38:48Z)
• DistGNN: Scalable Distributed Training for Large-Scale Graph Neural Networks [58.48833325238537]
  Full-batch training on Graph Neural Networks (GNN) to learn the structure of large graphs is a critical problem that needs to scale to hundreds of compute nodes to be feasible. In this paper, we presentGNN that optimize the well-known Deep Graph Library (DGL) for full-batch training on CPU clusters. Our results on four common GNN benchmark datasets show up to 3.7x speed-up using a single CPU socket and up to 97x speed-up using 128 CPU sockets.
  arXiv  Detail & Related papers  (2021-04-14T08:46:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.