Popular repositories Loading

1. Model-Compression-Research-Package Model-Compression-Research-Package Public

   Forked from IntelLabs/Model-Compression-Research-Package

   A library for researching neural networks compression and acceleration methods.

   Python

2. TensorRT TensorRT Public

   Forked from NVIDIA/TensorRT

   TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

   C++

3. MQBench MQBench Public

   Forked from ModelTC/MQBench

   Model Quantization Benchmark

   Shell

4. fairseq fairseq Public

   Forked from facebookresearch/fairseq

   Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

   Python

5. DeepSpeedExamples DeepSpeedExamples Public

   Forked from microsoft/DeepSpeedExamples

   Example models using DeepSpeed

   Python

6. FasterTransformer FasterTransformer Public

   Forked from NVIDIA/FasterTransformer

   Transformer related optimization, including BERT, GPT

   C++