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

December 29, 2024 Β· Declared Dead Β· πŸ› arXiv.org

πŸ’€ CAUSE OF DEATH: 404 Not Found
Code link is broken/dead
Authors Zongwu Wang, Fangxin Liu, Mingshuai Li, Li Jiang arXiv ID 2412.20501 Category cs.DC: Distributed Computing Citations 1 Venue arXiv.org Repository https://github.com/ACA-Lab-SJTU/token-ring} Last Checked 2 months ago
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}.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Distributed Computing

Died the same way β€” πŸ’€ 404 Not Found