DCAINIJun 29, 2024

Teola: Towards End-to-End Optimization of LLM-based Applications

arXiv:2407.00326v338 citationsHas Code
Originality Highly original
AI Analysis

This addresses performance bottlenecks for developers building complex LLM applications, offering a novel optimization approach beyond incremental improvements.

The paper tackles the problem of suboptimal end-to-end latency in LLM-based applications by proposing fine-grained orchestration with task primitives, achieving up to 2.09x speedup over existing systems.

Large language model (LLM)-based applications consist of both LLM and non-LLM components, each contributing to the end-to-end latency. Despite great efforts to optimize LLM inference, end-to-end workflow optimization has been overlooked. Existing frameworks employ coarse-grained orchestration with task modules, which confines optimizations to within each module and yields suboptimal scheduling decisions. We propose fine-grained end-to-end orchestration, which utilizes task primitives as the basic units and represents each query's workflow as a primitive-level dataflow graph. This explicitly exposes a much larger design space, enables optimizations in parallelization and pipelining across primitives of different modules, and enhances scheduling to improve application-level performance. We build Teola, a novel orchestration framework for LLM-based applications that implements this scheme. Comprehensive experiments show that Teola can achieve up to 2.09x speedup over existing systems across various popular LLM applications. The code is available at https://github.com/NetX-lab/Ayo.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes