OpenNMT / OpenNMT/CTranslate2

target_prefix latency

Open
#1,689 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Hello,

I noticed that when supplying a target_prefix to the translate_batch or generate_tokens method, the latencies for generating the supplied tokens is equivalent to the situation where they are not provided, while I would expect negligible latency because those tokens don't require any generation steps. I'm expecting the first step to be the generation of the token after the prefix tokens.

Am I missing something, or is this due to an inefficiency in ctranslate2's generation logic ?

Thanks,
Simon

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 with the translate_batch and generate_tokens entry points and reproduce the latency difference with and without target_prefix. Trace the generation logic to determine whether supplied prefix tokens are processed as generation steps; done means the observed behavior is explained and any inefficiency is identified with a focused regression check.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning, performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.