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
118 stars 28 forks source link

Lower test acceptance threshold #249

Closed szalpal closed 2 weeks ago

szalpal commented 2 weeks ago

Due to change in DALI (using nvImageCodec for image decoding), GPU memory consumption lowered when using fn.decoders.image. This PR adjusts the test values and makes the threshold related to the input data size.

dali-automaton commented 2 weeks ago

CI MESSAGE: [16433976]: BUILD STARTED

dali-automaton commented 2 weeks ago

CI MESSAGE: [16433976]: BUILD PASSED