Skip to content

[Misc] Benchmark Serving Script Support Appending Results #17028

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 2 commits into from
Apr 25, 2025
Merged

[Misc] Benchmark Serving Script Support Appending Results #17028

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cb43d4f
benchmark serving update
LucasWilkinson Apr 22, 2025
4541e83
format
LucasWilkinson Apr 22, 2025
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
31 changes: 20 additions & 11 deletions benchmarks/benchmark_serving.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -707,7 +707,7 @@ def main(args: argparse.Namespace):
))

# Save config and results to json
if args.save_result:
if args.save_result or args.append_result:
result_json: dict[str, Any] = {}

# Setup
Expand All @@ -728,6 +728,14 @@ def main(args: argparse.Namespace):
raise ValueError(
"Invalid metadata format. Please use KEY=VALUE format."
)
# Traffic
result_json["request_rate"] = (args.request_rate if args.request_rate
< float("inf") else "inf")
result_json["burstiness"] = args.burstiness
result_json["max_concurrency"] = args.max_concurrency

# Merge with benchmark result
result_json = {**result_json, **benchmark_result}
Comment on lines +737 to +738
Copy link
Member

@DarkLight1337 DarkLight1337 Apr 23, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We should merge the results after filtering fields from result_json in L747

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This appears to have been a bug since the keys filtered in L747 don't exist till after the merge, so that filter currently does nothing and the results.json still has the keys that were supposed to filtered (when run without this change)

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I see, thanks for explaining


if not args.save_detailed:
# Remove fields with too many data points
Expand All @@ -738,15 +746,6 @@ def main(args: argparse.Namespace):
if field in result_json:
del result_json[field]

# Traffic
result_json["request_rate"] = (args.request_rate if args.request_rate
< float("inf") else "inf")
result_json["burstiness"] = args.burstiness
result_json["max_concurrency"] = args.max_concurrency

# Merge with benchmark result
result_json = {**result_json, **benchmark_result}

# Save to file
base_model_id = model_id.split("/")[-1]
max_concurrency_str = (f"-concurrency{args.max_concurrency}"
Expand All @@ -756,7 +755,12 @@ def main(args: argparse.Namespace):
file_name = args.result_filename
if args.result_dir:
file_name = os.path.join(args.result_dir, file_name)
with open(file_name, "w", encoding='utf-8') as outfile:
with open(file_name,
mode="a+" if args.append_result else "w",
encoding='utf-8') as outfile:
# Append a newline.
if args.append_result and outfile.tell() != 0:
outfile.write("\n")
json.dump(result_json, outfile)
save_to_pytorch_benchmark_format(args, result_json, file_name)

Expand Down Expand Up @@ -888,6 +892,11 @@ def main(args: argparse.Namespace):
help="When saving the results, whether to include per request "
"information such as response, error, ttfs, tpots, etc.",
)
parser.add_argument(
"--append-result",
action="store_true",
help="Append the benchmark result to the existing json file.",
)
parser.add_argument(
"--metadata",
metavar="KEY=VALUE",
Expand Down