用无损压缩加速GPU通信，不改代码也能提速近50%。
UCCL-Zip: Lossless Compression Supercharged GPU Communication
- 将无损压缩嵌入GPU通信原语，无需修改程序接口。
- 实测强化学习权重同步加速47.5%，推理延迟降低10%。
- 适合大规模模型训练与推理场景，保持数值精确性。
大语言模型的快速发展使GPU通信成为关键瓶颈。以往方法通过量化或有损压缩减少通信量，但引入数值误差，影响收敛性、准确性和稳定性。本文提出UCCL-Zip，一种统一设计，将无损压缩直接集成到GPU通信原语中，支持点对点（P2P）和集体通信，无需修改用户接口且不损失数值正确性。对于点对点通信，Uzip-P2P采用分发-发送流水线，在早期暴露可传输数据，并将压缩与通信重叠，通过大块数据操作保持高GPU效率；对于集体通信，Uzip-NCCL通过融合执行将压缩集成至NCCL持久内核模型，消除冗余内存流量和内核启动。在真实负载下，UCCL-Zip将强化学习权重同步速度提升最高47.5%，并降低vLLM端到端推理延迟达10%，全程无需应用更改。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。