Dynamic shape computations have become critical in modern machine learning
workloads, especially in emerging large language models. The success of these
models has driven demand for deploying them to a diverse set of backend
environments. In this paper, we present Relax, a compiler abstraction for
optimizing end-to-end dynamic machine learning workloads. Relax introduces
first-class symbolic shape annotations to track dynamic shape computations
globally across the program. It also introduces a cross-level abstraction that
encapsulates computational graphs, loop-level tensor programs, and library
calls in a single representation to enable cross-level optimizations. We build
an end-to-end compilation framework using the proposed approach to optimize
dynamic shape models. Experimental results on large language models show that
Relax delivers performance competitive with state-of-the-art hand-optimized
systems across platforms and enables deployment of emerging dynamic models to a
broader set of environments, including mobile phones, embedded devices, and web
browsers.

Relax 是一种编译器抽象，通过引入一流的符号形状注释来全局跟踪动态形状计算，从而实现端到端的动态机器学习工作负载的优化，并且在各种平台上提供与手动优化系统相媲美的性能，使新兴动态模型能够在更广泛的环境中部署。

放松：端到端动态机器学习的可组合抽象

Relax: Composable Abstractions for End-to-End Dynamic Machine Learning

30 million Optical Coherence Tomography (OCT) imaging tests are issued
annually to diagnose various retinal diseases, but accurate diagnosis of OCT
scans requires trained eye care professionals who are still prone to making
errors. With better systems for diagnosis, many cases of vision loss caused by
retinal disease could be entirely avoided. In this work, we present ReLaX, a
novel deep learning framework for explainable, accurate classification of
retinal pathologies which achieves state-of-the-art accuracy. Furthermore, we
emphasize producing both qualitative and quantitative explanations of the
model's decisions. While previous works use pixel-level attribution methods for
generating model explanations, our work uses a novel retinal layer attribution
method for producing rich qualitative and quantitative model explanations.
ReLaX determines the importance of each retinal layer by combining heatmaps
with an OCT segmentation model. Our work is the first to produce detailed
quantitative explanations of a model's predictions in this way. The combination
of accuracy and interpretability can be clinically applied for accessible,
high-quality patient care.

本论文提出了一种新的深度学习框架 ReLaX，用于解释性和准确的视网膜病理分类，通过热图和 OCT 分割模型结合以确定每个视网膜层的重要性，并产生丰富的定性和定量模型解释，该模型结合了在精度和可解释性方面的优势，提高了患者的视网膜疾病诊断水平。