pith. sign in

arxiv: 2305.10427 · v1 · pith:KUDANJF2new · submitted 2023-05-17 · 💻 cs.CL · cs.AI· cs.LG

Accelerating Transformer Inference for Translation via Parallel Decoding

classification 💻 cs.CL cs.AIcs.LG
keywords decodingparalleltranslationautoregressiveinferencealgorithmsformulationmethods
0
0 comments X
read the original abstract

Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network architectures and learning-based methods to solve this issue, which are expensive and require changes to the MT model, trading inference speed at the cost of the translation quality. In this paper, we propose to address the problem from the point of view of decoding algorithms, as a less explored but rather compelling direction. We propose to reframe the standard greedy autoregressive decoding of MT with a parallel formulation leveraging Jacobi and Gauss-Seidel fixed-point iteration methods for fast inference. This formulation allows to speed up existing models without training or modifications while retaining translation quality. We present three parallel decoding algorithms and test them on different languages and models showing how the parallelization introduces a speedup up to 38% w.r.t. the standard autoregressive decoding and nearly 2x when scaling the method on parallel resources. Finally, we introduce a decoding dependency graph visualizer (DDGviz) that let us see how the model has learned the conditional dependence between tokens and inspect the decoding procedure.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SURF: Separation via Unsupervised Remixing Flow

    cs.SD 2026-06 unverdicted novelty 6.0

    SURF uses teacher-student remixing within a flow-matching framework to achieve unsupervised source separation and reports new state-of-the-art results on audio and image benchmarks.

  2. From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap

    cs.SE 2024-10 unverdicted novelty 4.0

    A semi-structured thematic synthesis identifies core challenges in FM selection, alignment, prompting, orchestration, testing, deployment, and cross-cutting concerns like observability for production-ready FMware.

  3. Small Language Models (SLMs) Can Still Pack a Punch: A survey (updated 2026)

    cs.CL 2025-01 unverdicted novelty 2.0

    A literature survey of Small Language Models (1-8B parameters) that can perform comparably or better than larger models, covering general-purpose and task-specific approaches plus creation techniques.