damccorm commented on code in PR #41200:
URL: https://github.com/apache/beam/pull/41200#discussion_r4565989996
##########
.github/workflows/beam_Inference_Python_Benchmarks_Dataflow.yml:
##########
@@ -260,9 +260,9 @@ jobs:
arguments: |
-PloadTest.mainClass=apache_beam.testing.benchmarks.inference.pytorch_image_captioning_benchmarks
\
-Prunner=DataflowRunner \
- -PpythonVersion=3.11 \
+ -PpythonVersion=3.12 \
-PloadTest.requirementsTxtFile=apache_beam/ml/inference/pytorch_image_captioning_requirements.txt
\
- '-PloadTest.args=${{
env.beam_Inference_Python_Benchmarks_Dataflow_test_arguments_13 }} --device=GPU
--worker_accelerator=type=nvidia-tesla-t4,count=1,install-nvidia-driver=true
--mode=batch
--job_name=benchmark-tests-pytorch-image-captioning-batch-${{env.NOW_UTC}}
--metrics_table=torch_inference_image_captioning_batch_gpu
--output_table=apache-beam-testing.beam_run_inference.result_torch_inference_image_captioning_batch_gpu'
\
+ '-PloadTest.args=${{
env.beam_Inference_Python_Benchmarks_Dataflow_test_arguments_13 }} --device=GPU
--experiments=worker_accelerator=type:nvidia-tesla-t4;count:1;install-nvidia-driver:5xx
--sdk_container_image=us.gcr.io/apache-beam-testing/python-postcommit-it/tensor_rt:latest
--num_workers=30 --disk_size_gb=100 --mode=batch
--job_name=benchmark-tests-pytorch-image-captioning-batch-${{env.NOW_UTC}}
--metrics_table=torch_inference_image_captioning_batch_gpu
--output_table=apache-beam-testing.beam_run_inference.result_torch_inference_image_captioning_batch_gpu'
\
Review Comment:
Why are we changing these parameters? (specifically num_workers and
disk_size_gb both impact what the benchmark is really doing)
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
