Full-graph GNN training delivers high accuracy but scales poorly on multi-server clusters due to heavy, irregular internode embedding exchanges. We present SNI-GNN, a SmartNICassisted full-graph training system that reduces communication while preserving accuracy by predicting remote embeddings innetwork. SNI-GNN deploys a lightweight linear-trend predictor on SmartNICs to refine cached historical embeddings, coupled with an importance-based boundary-node sampling policy and an asynchronous DPU-GPU data pipeline with intermediateresult reuse. We provide error and convergence bounds showing that predictor bias remains controlled under bounded secondorder dynamics and yields standard non-convex convergence with inexact gradients. Implemented on NVIDIA BlueField-3, SNI-GNN integrates with state-of-the-art full-graph systems, cuts communication by 21-45%, achieves 1.3-3.6 $\times$ end-to-end speedups over BNS-GCN and up to $1.29 \times$ over baseline SANCUS, with accuracy loss $\leq 0.01$, and scales efficiently to 16 GPUs on graphs with up to tens of millions of edges. These results indicate SmartNIC-based in-network prediction is a practical complement to partitioning and compression techniques for communicationefficient full-graph GNN training at scale.
Guofan Yu, Sitian Chen, Zhenheng Tang et al.· IEEE International Conferenc...· 0 citations
It is well established that the reasoning capabilities of large language models (LLMs) can be improved by applying reinforcement learning (RL) in a post-training stage. In a standard RL iteration, the current model (the policy) generates experience through rollouts, and the resulting data is then used to update the policy during training. High-performance RL frameworks such as StreamRL and AReaL employ a disaggregated architecture and asynchronous rollouts to better exploit both rollout and training resources, thereby increasing overall system throughput. Nonetheless, across varying RL setups (e.g., hardware configurations, model scales, staleness levels, and hyperparameters) and under changing workloads, it remains common for both rollout and training resources to experience idle periods. In this paper, we present BiDiRL, a hybrid time-space multiplexing architecture for asynchronous, disaggregated RL designed to reduce resource idleness. First, we develop a hot-switch runtime that enables rapid switching between rollout and training resources with negligible overhead. Second, we propose a static, scheduling-aware planner based on time-performance modeling that chooses a hot-switch-friendly resource partition, so that rollout and training durations are roughly balanced at a coarse level. Third, at execution time, we introduce a bidirectional scheduler that further exploits runtime bubbles through fine-grained resource switching, allowing the bottleneck stage to temporarily borrow idle resources from the other pool. Across a wide range of workloads, datasets, and models on two 32-GPU testbeds, BiDiRL increases RL training throughput by up to 1.94x compared with RL systems including veRL, AReaL, and ROLL, without affecting convergence behavior.
Zhiqiang Tan, Maoxin Wang, Sijie Wang et al.· 0 citations
Diffusion models are increasingly deployed as production visual-generation services, where serving high-resolution image and long video generation is often limited by GPU memory. Popular memory-saving techniques such as weight offloading, sharding, and VAE slicing are often not practical because they tend to introduce significant performance overhead. In this paper, we present Xema, a memory-efficient diffusion serving system that exploits predictable tensor lifetimes for trace-guided memory optimization. For each request template, Xema derives an offline memory trace to identify short memory-pressure intervals and applies memory mitigation only within these intervals and only by the amount needed to fit the target GPU budget. Xema further constructs a static memory layout for tensors with predictable lifetimes, reducing fragmentation-induced reserved memory and making offline memory reasoning reliable at runtime. Built on this memory optimization layer, Xema introduces an offline planner that jointly selects parallelism, concurrency, and memory control under GPU memory and SLO constraints. The selected plan is stored in a plan table and directly used by the online serving runtime. We implement Xema on production diffusion pipelines and evaluate it with Flux.2, CogVideoX-5B, and LTX-2. Compared with existing serving configurations, Xema improves SLO attainment by up to 3.7x and reduces planning cost from 6.3 hours to 197 seconds compared with grid search.
Xueze Kang, Guangyu Xiang, Suyi Li et al.· 1 citation
LLM serving is increasingly dominated by long and dynamic decode workloads from agents, reasoning models, and extended conversations. When bursty long-context demand exceeds deployed capacity, existing serving systems typically scale out by launching additional serving instances with model replicas. This instance-level elasticity increases KV capacity only by provisioning another full copy of the model, inheriting startup latency, memory overhead, and batch fragmentation. We present KernelFlume, a decode-centric architecture that disaggregates the stable projection/FFN path from core-attention computation: weight nodes execute dense projection/FFN kernels, while weightless attention nodes store token-range KV partitions and scale with request-state demand. To make this separation elastic, KernelFlume maintains a routing table that maps token ranges to attention-node endpoints. It updates routes at token boundaries and uses host-visible graph signals to drive pre-registered UCX endpoint communication outside the captured CUDA Graph. To preserve low per-token latency after disaggregation, KernelFlume combines query-first core-attention dispatch with inter-layer kernel pipelining, overlapping remote attention and communication with local projection/FFN work. On real GPU testbeds (intra-node A6000 and cross-node H100), under a dynamic long-context agentic workload serving Llama-3.1-8B, KernelFlume sustains flat p99 TPOTs of ~74 ms on A6000 and ~34 ms on H100, while lowering cost per million output tokens by up to 32% and 61%, respectively, relative to full-instance elastic scaling with ServerlessLLM, a state-of-the-art instance-startup method. Replaying the same trace at larger model scale in simulation projects a 56--66% cost reduction over ServerlessLLM, widening to 80--85% with cheaper heterogeneous attention-node hardware and persisting into the million-token context range.
Guangyu Xiang, Xueze Kang, Lin Zhang et al.· arXiv.org· 1 citation