Merge branch 'master' into sampling

CHANGELOG.md

@@ -10,12 +10,20 @@ Note that Sockeye has checks in place to not translate with an old model that wa
 
 Each version section may have have subsections for: _Added_, _Changed_, _Removed_, _Deprecated_, and _Fixed_.
 
-## [1.18.61]
+## [1.18.63]
 ### Added
 - Adding translation sampling via `--sample [N]`. This causes the decoder to sample each next step from the target distribution probabilities at each
   timestep. An optional value of `N` causes the decoder to sample only from the top `N` vocabulary items for each hypothesis at each timestep (the
   default is 0, meaning to sample from the entire vocabulary).
 
+## [1.18.62]
+### Added
+- Add option to make `TranslatorInputs` directly from a dict.
+
+## [1.18.61]
+### Changed
+- Update to MXNet 1.3.1. Removed requirements/requirements.gpu-cu{75,91}.txt as CUDA 7.5 and 9.1 are deprecated.
+
 ## [1.18.60]
 ### Fixed
 - Performance optimization to skip the softmax operation for single model greedy decoding is now only applied if no translation scores are required in the output.

sockeye/__init__.py

@@ -11,4 +11,4 @@
 # express or implied. See the License for the specific language governing
 # permissions and limitations under the License.
 
-__version__ = '1.18.61'
+__version__ = '1.18.63'