Popular repositories

1. torchpipe torchpipe Public

   An Alternative for Triton Inference Server. Boosting DL Service Throughput 1.5-4x by Ensemble Pipeline Serving with Concurrent CUDA Streams for PyTorch/LibTorch Frontend and TensorRT/CVCUDA, etc., …

   C++ 127 12

2. torchpipe.github.io torchpipe.github.io Public

   Docs for torchpipe: https://github.com/torchpipe/torchpipe

   MDX 4 1

3. CV-CUDA CV-CUDA Public

   Forked from CVCUDA/CV-CUDA

   CV-CUDA™ for Pascal(sm61) and lower version of gcc

   C++ 1