Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Modifying the min queries constraint for the Offline scenario #1532

Merged
merged 1 commit into from
Dec 12, 2023
Merged

Modifying the min queries constraint for the Offline scenario #1532

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 12 additions & 3 deletions mlperf.conf
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,10 +57,19 @@ gptj.Server.target_latency = 20000

*.Offline.target_latency_percentile = 90
*.Offline.min_duration = 600000

# In Offline scenario, we always have one query. But LoadGen maps this to
# min_sample_count internally in Offline scenario, so set this to 24576 since
# the rule requires that Offline scenario run for at least 24576 samples.
*.Offline.min_query_count = 24576
# min_sample_count internally in Offline scenario. If the dataset size is larger
# than 24576 we limit the min_query_count to 24576 and otherwise we use
# the dataset size as the limit

resnet50.Offline.min_query_count = 24576
retinanet.Offline.min_query_count = 24576
dlrm-v2.Offline.min_query_count = 24576
bert.Offline.min_query_count = 10833
gptj.Offline.min_query_count = 13368
rnnt.Offline.min_query_count = 2513
3d-unet.Offline.min_query_count = 43

# These fields should be defined and overridden by user.conf.
*.SingleStream.target_latency = 10
Expand Down