Skip to content

[Benchmark] Keep going when a single benchmark fails #820

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

Merged
merged 1 commit into from
Oct 6, 2025
Merged

[Benchmark] Keep going when a single benchmark fails #820

Show file tree
Hide file tree
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
4 changes: 2 additions & 2 deletions .github/workflows/benchmark.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -169,7 +169,7 @@ jobs:
--only $IMPLS \
--only-match-mode prefix-with-baseline \
--baseline $BASELINE \
--exit-on-exception
--keep-going

# Relax the GPU
sleep 2m
Expand All @@ -185,7 +185,7 @@ jobs:
--baseline $BASELINE \
--output "$TEST_REPORTS_DIR/helionbench.json" \
--append-to-output \
--exit-on-exception
--keep-going

echo "✅ Completed benchmark for kernel: $kernel"
done
Expand Down
3 changes: 3 additions & 0 deletions benchmarks/run.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -989,6 +989,9 @@ def process_result(
if name not in KERNEL_METRIC_MAPPINGS[kernel_name]:
logger.info(f"ignoring {name}")
else:
if item == "":
# if benchmark failed, tritonbench emits empty string
item = 0.0
metrics[KERNEL_METRIC_MAPPINGS[kernel_name][name]].append(
float(item)
)
Expand Down
Loading