search

triton-inference-server / dali_backend

The Triton backend that allows running GPU-accelerated data pre-processing pipelines implemented in DALI's python API.
https://docs.nvidia.com/deeplearning/dali/user-guide/docs/index.html
MIT License
123 stars 29 forks source link

DALI vs CV-CUDA benchmark #172

Closed szalpal closed 1 year ago

szalpal commented 1 year ago

This is a benchmark for comparing CV-CUDA-based processing with DALI based processing.

CV-CUDA does not have a dedicated Triton backend, therefore we're using it in a Python backend. The CV-CUDA processing example has been acquired from CV-CUDA repository.

This PR does not introduce a new mechanism, it's just adding a new model to an existing benchmark template.