The rapid growth of large language models (LLMs) has made GPU communication a critical bottleneck. While prior work reduces communication volume via quantization or lossy compression, these approaches introduce numerical errors that can degrade convergence, accuracy, and stability. We present UCCL-Zip, a unified design that integrates lossless compression directly into GPU communication primitives. UCCL-Zip supports both point-to-point (P2P) and collective communication without modifying user-facing APIs or compromising numerical correctness. For P2P communication, Uzip-P2P employs a split-send pipeline that exposes transmissible data early and overlaps compression with communication, while preserving high GPU efficiency by operating on large data blocks. For collective communication, Uzip-NCCL integrates compression into NCCL's persistent kernel model via fused execution, eliminating redundant memory traffic and kernel launches. In real workloads, UCCL-Zip accelerates RL weight synchronization by up to 47.5% and reduces vLLM end-to-end inference latency by up to 10%, all without application changes.
@article{arxiv.2604.17172,
title = {UCCL-Zip: Lossless Compression Supercharged GPU Communication},
author = {Shuang Ma and Chon Lam Lao and Zhiying Xu and Zhuang Wang and Ziming Mao and Delong Meng and Jia Zhen and Jun Wu and Ion Stoica and Yida Wang and Yang Zhou},
journal= {arXiv preprint arXiv:2604.17172},
year = {2026}
}