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

Move GPU_DALI_ensemble test from L0 to L1 #201

Closed szalpal closed 1 year ago

szalpal commented 1 year ago

The GPU_DALI_ensemble test is always a bottleneck of the CI pipelines. This PR moves the test to the L1 stage, so that it will be triggered nightly.

dali-automaton commented 1 year ago

CI MESSAGE: [8688721]: BUILD STARTED

dali-automaton commented 1 year ago

CI MESSAGE: [8688721]: BUILD PASSED