OpenNMT / OpenNMT/CTranslate2

Support for RNN based decoder units

Open
#796 9 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
C++
Stars
4.7k
Forks
536
Avg merge
12h 12m
Merged PRs (30d)
4

Description

Are there any plans to support inference of heterogeneous encoder-decoder architectures where in we use transformer based encoder and RNN/LSTM based decoders ?

Would like to submit this as a new feature request.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue mentions no files, tests, or entry points. Start by locating the existing inference support for transformer encoder-decoder models and reviewing how decoder architectures are represented. Done means demonstrating inference for a transformer-based encoder paired with an RNN or LSTM decoder, with appropriate coverage for the supported heterogeneous architecture.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.