TokenRing: An Efficient Parallelism Framework for Infinite-Context LLMs via Bidirectional Communication

TL;DR

TokenRing introduces a bidirectional communication framework that significantly improves the scalability and efficiency of parallelizing long-context LLMs, reducing communication overhead and enhancing throughput.

Contribution

It proposes a novel fine-grained parallel framework leveraging bidirectional P2P communication and concurrent data transmission to optimize distributed Transformer performance.

Findings

Reduces communication overhead in long-sequence LLMs

Improves throughput and scalability of distributed Transformers

Enhances compatibility with various multi-GPU interconnects

Abstract

Efficient parallelization of Large Language Models (LLMs) with long sequences is essential but challenging due to their significant computational and memory demands, particularly stemming from communication bottlenecks in attention mechanisms. While sequence parallelism (SP) has been introduced as a potential solution, existing methods often suffer from limited scalability or inefficiency, rendering their effectiveness. Ring-Attention demonstrates the potential for scaling sequence processing but faces significant limitations due to its reliance on peer-to-peer (P2P) communication and inefficient utilization of network resources. As the degree of SP increases, the quadratic decrease in computation time per step contrasts sharply with the linear reduction in communication volume, exacerbating communication bottlenecks. To address these challenges, we propose TokenRing, a fine-grained parallel framework that leverages bidirectional P2P communication to effectively overlap computation and data transmission. By partitioning the attention block and concurrently transmitting Query and block outputs (i.e., $block\_out$ and $block\_lse$) within a fully connected mesh topology, TokenRing achieves significant reductions in communication overhead and better load balancing. These innovations improve the scalability and efficiency of distributed Transformer models, particularly for long-context sequences. Experimental results demonstrate that TokenRing enhances throughput and reduces communication latency. Moreover, its design adapts seamlessly to various multi-GPU interconnect solutions, such as Huawei Ascend, ensuring broad compatibility and cost-effectiveness for distributed LLM inference and training. The code is available at: \url{https://github.com/ACA-Lab-SJTU/token-ring}.