Skip to content
#graph neural networks Book Open access

PruneInfer: Exact Full-Neighborhood GNN Inference of Large Datasets on a Single GPU via Full Topology Pruning

Sep 2026 · Proceedings of the International Conference on Parallel Processing · pp. 501-511 · 0 citations · 28 references

TL;DR

PruneInfer is the only system on the authors' experimental configuration that maintains accuracy comparable to full-graph inference across all evaluated models and achieves up to 4.49 × speedup over DGL and up to 7.05 × speedup over GDL-GNN across the evaluated datasets.

Abstract

Graph neural network (GNN) inference in deployment often requires deterministic and exact predictions, which in turn require each inference run to aggregate complete dependency information from the full graph topology. However, over large graphs, full-graph forward propagation is usually infeasible on GPU due to limited memory, and slow on CPU due to slow computation. Existing systems address this limitation through exact full-neighborhood inference with different execution schemes. In these schemes, DGL-style systems repeatedly spill and reload intermediate embeddings between CPU and GPU, while GDL-style systems reduce this spill traffic by partitioning the graph but repeatedly transfer overlapping raw features and recompute overlapping intermediate embeddings across expanded subgraphs. This paper presents PruneInfer, an efficient single-GPU system for exact full-neighborhood GNN inference. PruneInfer fully prunes redundant topology across partitioned subgraphs and explicitly reuses previously computed intermediate embeddings to avoid redundant data movement and computation. To further reduce and hide communication overhead, PruneInfer incorporates F2-Cache, a frequency-guided two-tier cache, and a cross-layer asynchronous pipeline (CLAP). Experiments on four large real-world graphs and three representative GNN models show that PruneInfer achieves up to 4.49 × speedup over DGL and up to 7.05 × speedup over GDL-GNN across the evaluated datasets. PruneInfer is the only system on our experimental configuration that maintains accuracy comparable to full-graph inference across all evaluated models.

Read PDF

Similar papers

Preprint Aug 2026

CoRun: Padding is Simple and Efficient for Deterministic LLM Inference

CoRun is presented, a scheduling-based system that achieves deterministic inference without requiring batch invariance, and employs isolated prefill and fixed-shape batched decode to handle the two stages of LLM inference, respectively, leveraging CUDA graphs for efficient execution and simplified implementation.

Shiju Zhao, Jiacheng Yang, Qi-Hang Chen et al. · 2 citations
Jul 2026

Efficient GPU-Accelerated Local Subgraph Counting

A high-performance GPU solution for local subgraph counting that preserves SCOPE's tree-decomposition framework while explicitly resolving the tension between massive GPU parallelism and limited device memory is developed.

Qiao He, Yi-Ran Li, Man-Lung Yiu et al. · 0 citations

SparseEngine: Sparse-First Inference Engine

Long-context LLM agents accumulate interaction histories that strain KV-cache memory and attention computation. Although sparse attention reduces these costs, heterogeneous cache representations and workflows hinder integration with existing inference engines, while prior sparse-serving abstractions support only specif...

Jitai Hao, Quan-Sheng Gu, Qiang Huang et al. · 1 citation
Preprint Aug 2026

Every Expert Counts: ExactMoE for Memory-Efficient W4A16 Inference

ExactMoE, an inference design that applies symmetric group-128 four-bit weight quantization only to routed experts, stores those experts in kernel-native MARLIN form in pinned host memory, and executes all selected experts through a configurable GPU-resident slot cache and fused grouped MoE kernels, identifies a practi...

Amjad Saab · 0 citations
#machine learning Preprint Sep 2026

HiLoRe: What to Store, Compress, or Recompute for Efficient GRPO Training

HiLoRe is introduced, which allocates graph-attributed recovery units among high-precision storage, low-precision compression, and deterministic recomputation using measured recovery utility and update-conditioned approximation risk, and combines high-precision storage and deterministic recomputation with low-precision...

Xin-Rui Chen, Mengyang Li, Ou Wu et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.