From 27a200793786ff0ed09f9e70be1e93da42d8d805 Mon Sep 17 00:00:00 2001 From: Guillaume Klein Date: Thu, 16 Jul 2020 14:03:07 +0200 Subject: [PATCH] Bump version to 1.12.0 --- CHANGELOG.md | 19 ++++++++++++++++++- python/setup.py | 2 +- 2 files changed, 19 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index a020bb2ec..33ba47b7a 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -2,7 +2,24 @@ ### New features -* Support `float16` data type for model conversion (with `--quantization float16`) and computation (with `--compute_type float16`). FP16 execution requires a NVIDIA GPU with Compute Capability >= 7.0. +### Fixes and improvements + +## [v1.12.0](https://github.com/OpenNMT/CTranslate2/releases/tag/v1.12.0) (2020-07-16) + +### Changes + +* Docker images based on Ubuntu 16.04 are no longer updated + +### New features + +* Support `float16` data type for model conversion (with `--quantization float16`) and computation (with `--compute_type float16`). FP16 execution can improve performance by up to 50% on NVIDIA GPUs with Compute Capability >= 7.0. +* Add Docker images with newer CUDA versions, which can improve performance in some cases: + * `latest-ubuntu18-cuda10.0` (same as `latest-ubuntu18-gpu`) + * `latest-ubuntu18-cuda10.1` + * `latest-ubuntu18-cuda10.2` + * `latest-centos7-cuda10.0` (same as `latest-centos7-gpu`) + * `latest-centos7-cuda10.1` + * `latest-centos7-cuda10.2` * Allow setting a computation type per device (e.g. `Translator(..., compute_type={"cuda": "float16", "cpu": "int8"})` with the Python API) * [C++] Add `ModelReader` interface to customize model loading diff --git a/python/setup.py b/python/setup.py index 783f3c786..fe52f77bd 100644 --- a/python/setup.py +++ b/python/setup.py @@ -35,7 +35,7 @@ def _maybe_add_library_root(lib_name): setup( name="ctranslate2", - version="1.11.0", + version="1.12.0", license="MIT", description="Optimized inference engine for OpenNMT models", long_description=_get_long_description(),