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
121 stars 28 forks source link

Fix incorrect test definition for perf_analyer example #120

Closed szalpal closed 2 years ago

szalpal commented 2 years ago

This PR solves the problem of the perf_analyzer_example test, which has been sometimes failing. The testing conditions weren't correct - they assumed, that the throughput of the pipeline will always be in range 100..999 [ims/s]. We should allow it to be 0..9999 [ims/s], as these are sane values in proper circumstances.

Signed-off-by: szalpal mszolucha@nvidia.com

dali-automaton commented 2 years ago

CI MESSAGE: [4151342]: BUILD STARTED

dali-automaton commented 2 years ago

CI MESSAGE: [4152868]: BUILD STARTED

dali-automaton commented 2 years ago

CI MESSAGE: [4152868]: BUILD FAILED

dali-automaton commented 2 years ago

CI MESSAGE: [4152868]: BUILD FAILED

dali-automaton commented 2 years ago

CI MESSAGE: [4153407]: BUILD STARTED

dali-automaton commented 2 years ago

CI MESSAGE: [4152868]: BUILD FAILED

dali-automaton commented 2 years ago

CI MESSAGE: [4153407]: BUILD PASSED

dali-automaton commented 2 years ago

CI MESSAGE: [4170271]: BUILD STARTED

dali-automaton commented 2 years ago

CI MESSAGE: [4170271]: BUILD FAILED

dali-automaton commented 2 years ago

CI MESSAGE: [4179669]: BUILD STARTED

dali-automaton commented 2 years ago

CI MESSAGE: [4170271]: BUILD PASSED

dali-automaton commented 2 years ago

CI MESSAGE: [4179669]: BUILD PASSED