facebookresearch/fairseq

Is there a C++ version of Fairseq based on libtorch

Open

#5,540 opened on Sep 11, 2024

View on GitHub
 (0 comments) (0 reactions) (0 assignees)Python (29,107 stars) (6,224 forks)batch import
enhancementhelp wantedneeds triage

Description

🚀 Feature Request

A C++ version of Fairseq based on libtorch is required

Motivation

Pytorch and the entire python environment are too large after packaging, so use libtorch instead. However, the previous fairseq loaded model must also be loaded in C++, but no C++ version of fairseq has been found

Pitch

Provides a C++ version of fairseq based on libtorch

Alternatives

Additional context

Contributor guide

Tech stack
cpppytorch
Domain
machine learning
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
5
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
over 1 week
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
C++PyTorch/libtorchFairseq internalsSequence to sequence models
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
10
Research direction
Study the current Python fairseq library to understand model loading and inference. Look at PyTorch's C++ documentation and examples for exporting models to TorchScript. Consider creating a minimal C++ inference engine that loads a previously trained model and performs sequence to sequence generation. Review any existing issues or discussions about C++ deployment in the repository.