paper-with-me

Papers

Reducing the GPU Memory Bottleneck with Lossless Compression for ML -- Extended

2026-05-29 · Aditya K Kamath, Arvind Krishnamurthy, Marco Canini, Simon Peter arxiv

Machine learning (ML) training and inference often process data sets far exceeding GPU memory capacity, forcing them to rely on PCIe for on-demand tensor transfers, causing critical transfer bottlenecks. Lossy compression has been proposed to relieve bottlenecks but introduces workload-dependent accuracy loss, making it complex or even prohibitive to use in existing ML deployments. We explore lossless compression as an alternative that avoids this deployment complexity. We identify where lossless compression can be integrated into ML pipelines while minimizing interference with GPU execution. Based on our findings, we introduce Invariant Bit Packing (IBP), a novel lossless compression algorithm designed to minimize data transfer time for ML. IBP identifies and eliminates invariant bits across groups of tensors, improving throughput through GPU-optimized decompression that leverages warp parallelism, low-overhead bit operations, and asynchronous PCIe transfers. We provide easy-to-use APIs, showcasing them by adding IBP support to GNN training, as well as DLRM and LLM inference frameworks. IBP achieves, on average, 74% faster GNN training, 180% faster DLRM embedding lookup, and 24% faster LLM inference.

📄 PDF Abstract BibTeX arXiv:2605.30728

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

LoMA: Lossless Compressed Memory Attention

2024-01-16 · Yumeng Wang, Zhenyang Xiao

Large Language Models (LLMs) face limitations due to the high demand on GPU memory and computational resources when handling long contexts. While sparsify the Key-Value (KV) cache of transformer model is a typical strate…

GPU

ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression

2026-03-18 · Ruibo Fan, Xiangrui Yu, Xinglin Pan, Zeyu Li 외 arxiv

Lossless model compression holds tremendous promise for alleviating the memory and bandwidth bottlenecks in bit-exact Large Language Model (LLM) serving. However, existing approaches often result in substantial inference…

Model Compression

Lossless KV Cache Compression to 2%

2024-10-20 · Zhen Yang, J. N. Han, Kan Wu, Ruobing Xie 외

Large language models have revolutionized data processing in numerous domains, with their ability to handle extended context reasoning receiving notable recognition. To speed up inference, maintaining a key-value (KV) ca…

Dimensionality ReductionQuantization

DeltaKV: Residual-Based KV Cache Compression via Long-Range Similarity

2026-02-08 · Jitai Hao, Qiang Huang, Yaowei Wang, Min Zhang 외 arxiv

The deployment of efficient long-context LLMs in applications like autonomous agents, long-chain reasoning, and creative writing is fundamentally bottlenecked by the linear growth of KV cache memory. Existing compression…

ENEC: A Lossless AI Model Compression Method Enabling Fast Inference on Ascend NPUs

2026-03-28 · Jinwu Yang, Jiaan Wu, Zedong Liu, Xinyang Ma 외 arxiv

The rapid scaling of Large Language Models presents significant challenges for their deployment and inference, particularly on resource-constrained specialized AI hardware accelerators such as Huawei's Ascend NPUs, where…

Model Compression