marian-nmt Goto Github PK

amun

Fast stand-alone C++ decoder for RNN-based NMT models

amun-regression-tests

Regression tests for Amun

cub

[ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl

demo-paper

Demo paper for Marian. Submitted to ACL 2018 demo session

docmt23

extract-lex

Lexicon extractor from Moses

faiss

A library for efficient similarity search and clustering of dense vectors.

fastbpe

Fast BPE

fbgemm

FB (Facebook) + GEMM (General Matrix-Matrix Multiplication) - https://code.fb.com/ml-applications/fbgemm/

infinibatch

Efficient, check-pointed data loading for deep learning with massive data sets.

intgemm

int8_t and int16_t matrix multiply based on https://arxiv.org/abs/1705.01991

marian

Fast Neural Machine Translation in C++

marian-benchmarks

Performance benchmarks for Marian

marian-dev

Fast Neural Machine Translation in C++ - development repository

marian-example-library

marian-examples

Examples, tutorials and use cases for Marian, including our WMT-2017/18 baselines.

marian-nmt.github.io

The official website of the Marian toolkit

marian-regression-tests

Regression tests for the marian-dev repository

marian-tensorboard

TensorBoard integration for Marian NMT

moses-scorers

Scorers from Moses as a separate library.

moses-scripts

Some useful scripts from Moses

mtm2017-tutorial

additional files for Machine Translation Marathon 2017 tutorial

nccl

Optimized primitives for collective multi-GPU communication

pathie-cpp

Small C++ library for crossplatform Unicode path management

pybind11

Seamless operability between C++11 and Python

pytorch-erf

Implementation of the ERF function for pytorch (CPU and GPU)

ruy

sacrebleu

Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

sentencepiece

Unsupervised text tokenizer for Neural Network-based text generation.

simd_utils

A header only library implementing common mathematical functions using SIMD intrinsics