Plato: Plan to Efficient Decode for Large Language Model Inference

Shuowei Jin, Xueshen Liu, Yongji Wu, Haizhong Zheng, Qingzhao Zhang, Atul Prakash, Matthew Lentz, Danyang Zhuo, Feng Qian, Zhuoqing Mao

Keywords: Efficient LLM Inference

TL;DR: Plan to exploit parallelism structure to break the autoregressive nature of LLM inference.

Abstract:

Large language models (LLMs) have achieved remarkable success in natural language tasks, but their inference incurs substantial computational and memory overhead.
To improve efficiency, parallel decoding methods like Skeleton-of-Thought (SoT) decompose prompts into sub-problems for concurrent processing. However, these methods significantly compromise answer quality by treating semantically linked sub-problems as independent.
We propose Plato, a novel approach that co-designs algorithms and systems for semantic-aware parallel decoding. Plato leverages LLMs to organize sub-problems into a dependency graph based on logical and causal relationships, enabling concurrent decoding of non-dependent nodes while preserving answer coherence and quality.
To further enhance efficiency, Plato pipelines planning and node decoding stages, implements a global context cache, and carefully structures node inference prompts to maximize key-value cache reuse and minimize overhead. Our evaluations show that Plato improves throughput by up to 68% over autoregressive decoding while achieving a 40% net win rate in answer quality. Compared to SoT, Plato demonstrates a remarkable 90% quality net-win rate. Ablation studies reveal that our pipeline design improves speedup by 29%, while our KV cache reuse optimization reduces overhead by 75%.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 308