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
120 stars 28 forks source link

Add `"depleted"` operator trace handling #187

Closed szalpal closed 1 year ago

szalpal commented 1 year ago

Should the VideoInput operator be properly working with ExternalSource in the same pipeline, DALI Backend needs to properly handle the "depleted" operator trace. This trace, defined in DALI, specifies when a given operator needs more data at the input. Refers to https://github.com/NVIDIA/DALI/pull/4794

dali-automaton commented 1 year ago

CI MESSAGE: [7990559]: BUILD STARTED

dali-automaton commented 1 year ago

CI MESSAGE: [7990559]: BUILD FAILED

dali-automaton commented 1 year ago

CI MESSAGE: [8014491]: BUILD STARTED

dali-automaton commented 1 year ago

CI MESSAGE: [8014491]: BUILD FAILED

dali-automaton commented 1 year ago

CI MESSAGE: [8023757]: BUILD STARTED

dali-automaton commented 1 year ago

CI MESSAGE: [8023757]: BUILD PASSED