OpenNMT / OpenNMT/CTranslate2

Can batch translation on CPU result in different output?

Open
#693 8 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

I have a CPU model that produces different outputs for the same strings at different times.

I think it could be related to the bug from https://github.com/OpenNMT/CTranslate2/issues/546 where batch translation yielded different results on GPU, I'm currently using CTranslate2 1.20.1 so there's a lot of updates I'm missing.

Alternatively, I recall that on GPU, batch translation can have slightly different numerical results, and am curious whether the same can happen with CPU models and batch translation?

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

Start by reproducing the differing CPU batch-translation outputs with CTranslate2 1.20.1 using identical strings across separate runs. Compare the behavior with issue 546 and determine whether the result is expected numerical variation or a reproducible bug; done means documenting that conclusion with a minimal reproduction.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Bug
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.