Dynamic Transformer for Efficient Machine Translation on Embedded Devices
원문 초록
The Transformer architecture is widely used for machine translation tasks. However, its resource-intensive nature makes it challenging to implement on constrained embedded devices, particularly where available hardware resources can vary at run-time. We propose a dynamic machine translation model that scales the Transformer architecture based on the available resources at any particular time. The proposed approach, 'Dynamic-HAT', uses a HAT SuperTransformer as the backbone to search for SubTransformers with different accuracy-latency trade-offs at design time. The optimal SubTransformers are sampled from the SuperTransformer at run-time, depending on latency constraints. The Dynamic-HAT is tested on the Jetson Nano and the approach uses inherited SubTransformers sampled directly from the SuperTransformer with a switching time of <1s. Using inherited SubTransformers results in a BLEU score loss of <1.5% because the SubTransformer configuration is not retrained from scratch after sampling. However, to recover this loss in performance, the dimensions of the design space can be reduced to tailor it to a family of target hardware. The new reduced design space results in a BLEU score increase of approximately 1% for sub-optimal models from the original design space, with a wide range for performance scaling between 0.356s - 1.526s for the GPU and 2.9s - 7.31s for the CPU.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MathOptAI.jl: Embed trained machine learning predictors into JuMP models
CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillation
ConsumerBench: Benchmarking Generative AI Applications on End-User Devices
Versatile and Fast Location-Based Private Information Retrieval with Fully Homomorphic Encryption over the Torus
SecONNds: Secure Outsourced Neural Network Inference on ImageNet
Gender Bias in English-to-Greek Machine Translation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.