ray-serve topic

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., Bac...

torchpipe

This is suite of the hands-on training materials that shows how to scale CV, NLP, time-series forecasting workloads with Ray.

ray-project