20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Update benchmark_serving.py to read and write json-datasets, results in UTF8, for better compatibility with Windows (#8997)

Browse Source
This commit is contained in:
vlsav 2024-10-01 21:07:06 +03:00 committed by GitHub
parent 4f341bd4bf
commit 22f5851b80
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
benchmarks/benchmark_serving.py
View File

@ -90,7 +90,7 @@ def sample_sharegpt_requests(
fixed_output_len: Optional[int] = None, fixed_output_len: Optional[int] = None,
) -> List[Tuple[str, int, int, None]]: ) -> List[Tuple[str, int, int, None]]:
# Load the dataset. # Load the dataset.
with open(dataset_path) as f: with open(dataset_path, encoding='utf-8') as f:
dataset = json.load(f) dataset = json.load(f)
# Filter out the conversations with less than 2 turns. # Filter out the conversations with less than 2 turns.
dataset = [data for data in dataset if len(data["conversations"]) >= 2] dataset = [data for data in dataset if len(data["conversations"]) >= 2]
@ -139,7 +139,7 @@ def sample_sonnet_requests(
), "'args.sonnet-input-len' must be greater than 'args.prefix-input-len'." ), "'args.sonnet-input-len' must be greater than 'args.prefix-input-len'."
# Load the dataset. # Load the dataset.
with open(dataset_path) as f: with open(dataset_path, encoding='utf-8') as f:
poem_lines = f.readlines() poem_lines = f.readlines()
# Tokenize the poem lines. # Tokenize the poem lines.
@ -726,7 +726,7 @@ 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") as outfile: with open(file_name, "w", encoding='utf-8') as outfile:
json.dump(result_json, outfile) json.dump(result_json, outfile)