bytedance / lightseq
LightSeq: A High Performance Inference Library for Sequence Processing and Generation
| Jan | FEB | Mar |
| 06 | ||
| 2020 | 2021 | 2022 |

See what the GitHub community is most excited about today.
LightSeq: A High Performance Inference Library for Sequence Processing and Generation
The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"
cuML - RAPIDS Machine Learning Library
Cooperative primitives for CUDA C++.
FSA/FST algorithms, differentiable, with PyTorch compatibility.
This is a Tensor Train based compression library to compress sparse embedding tables used in large-scale machine learning models such as recommendation and natural language processing. We showed this library can reduce the total model size by up to 100x in Facebook’s open sourced DLRM model while achieving same model quality. Our implementation …
Squeeze-and-Excitation Networks