NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI, #782 most downloaded on PyPI
Fast inference engine for Transformer models
Latest stable
4.9.0
Last release 12 days ago
10 Nov 2026
Release timing varies
gaps range from 2 weeks to 7 months
Nearly every release is documented
notes for 60 of the last 60 stable releases
Nothing withdrawn
no release was ever pulled
6 years old
66 releases · first in 2021
Drag across the ruler to compare, or tap a release to open it.
Generation option no_repeat_ngram_size to prevent the repetitions of N-grams with a minimum size
no_repeat_ngram_size to prevent the repetitions of N-grams with a minimum sizereturn_alternatives mode when the target prefix is longer than max_decoding_length<pad> token when converting MarianMT models from Transformers: this token is only used to start the decoder from a zero embedding, but it is not included in the original Marian modelOpenNMTTFConverterV2.from_configFix missing final bias in some MarianMT models converted from Transformers
ctranslate2::float16_t in the public headers that is required to use some functionsYour coding agent can read these notes before it upgrades. Set up the MCP server →
Support conversion of decoder-only Transformer models trained with OpenNMT-tf
facebook/bart-large-cnnmax_input_length after all special tokens have been added to the inputSupport Meta's OPT models via the Transformers converter
transformer_lm modelsAdd a converter for Hugging Face's Transformers. The following models are currently supported:
ctranslate2.converters.OpenNMTTFConverterV2Do not return scores for empty outputs when return_scores is disabled
return_scores is disabledOne column per quarter.