Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model

Alexandre Berard; Vassilina Nikoulina; Yeskendir Koishekenov

Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2212.09811 v3 pith:YPKEIISB submitted 2022-12-19 cs.CL cs.AIcs.LG

Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model

Yeskendir Koishekenov , Alexandre Berard , Vassilina Nikoulina This is my paper

classification cs.CL cs.AIcs.LG

keywords expertsmodelpruningtranslationfurtherlanguage-specificmachinemultilingual

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

0 comments

read the original abstract

The recently released NLLB-200 is a set of multilingual Neural Machine Translation models that cover 202 languages. The largest model is based on a Mixture of Experts architecture and achieves SoTA results across many language pairs. It contains 54.5B parameters and requires at least four 32GB GPUs just for inference. In this work, we propose a pruning method that enables the removal of up to 80% of experts without further finetuning and with a negligible loss in translation quality, which makes it feasible to run the model on a single 32GB GPU. Further analysis suggests that our pruning metrics can identify language-specific experts.

discussion (0)

Forward citations

Cited by 1 Pith paper

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

Communication-Aware Placement and Pruning for Efficient Mixture-of-Experts Inference
cs.DC 2026-07 conditional novelty 6.0

Communication-aware expert placement plus device-level pruning yields 1.23–1.86× MoE inference throughput and better accuracy at equal speedup than load-balance or sequential baselines.