xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-15 11:36:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Benchmark Serving Script Support Appending Results (#17028)

Browse Source 
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
This commit is contained in:
Lucas Wilkinson 2025-04-25 01:53:55 -04:00 committed by GitHub
parent 2f54045508
commit 881f735827
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 20 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
benchmarks/benchmark_serving.py
View File

@ -713,7 +713,7 @@ def main(args: argparse.Namespace):
)) ))
# Save config and results to json # Save config and results to json
if args.save_result: if args.save_result or args.append_result:
result_json: dict[str, Any] = {} result_json: dict[str, Any] = {}
# Setup # Setup
@ -734,6 +734,14 @@ def main(args: argparse.Namespace):
raise ValueError( raise ValueError(
"Invalid metadata format. Please use KEY=VALUE format." "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}
if not args.save_detailed: if not args.save_detailed:
# Remove fields with too many data points # Remove fields with too many data points
@ -744,15 +752,6 @@ def main(args: argparse.Namespace):
if field in result_json: if field in result_json:
del result_json[field] 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 # Save to file
base_model_id = model_id.split("/")[-1] base_model_id = model_id.split("/")[-1]
max_concurrency_str = (f"-concurrency{args.max_concurrency}" max_concurrency_str = (f"-concurrency{args.max_concurrency}"
@ -762,7 +761,12 @@ def main(args: argparse.Namespace):
file_name = args.result_filename file_name = args.result_filename
if args.result_dir: if args.result_dir:
file_name = os.path.join(args.result_dir, file_name) 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) json.dump(result_json, outfile)
save_to_pytorch_benchmark_format(args, result_json, file_name) save_to_pytorch_benchmark_format(args, result_json, file_name)
@ -894,6 +898,11 @@ if __name__ == "__main__":
help="When saving the results, whether to include per request " help="When saving the results, whether to include per request "
"information such as response, error, ttfs, tpots, etc.", "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( parser.add_argument(
"--metadata", "--metadata",
metavar="KEY=VALUE", metavar="KEY=VALUE",