From 8f4afe0f654cb2f583925ec4cc5f741214148609 Mon Sep 17 00:00:00 2001 From: vlsav Date: Tue, 1 Oct 2024 21:07:06 +0300 Subject: [PATCH] Update benchmark_serving.py to read and write json-datasets, results in UTF8, for better compatibility with Windows (#8997) Signed-off-by: Sumit Dubey --- benchmarks/benchmark_serving.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/benchmarks/benchmark_serving.py b/benchmarks/benchmark_serving.py index 996a92d2a8b3d..56c37b241a359 100644 --- a/benchmarks/benchmark_serving.py +++ b/benchmarks/benchmark_serving.py @@ -90,7 +90,7 @@ def sample_sharegpt_requests( fixed_output_len: Optional[int] = None, ) -> List[Tuple[str, int, int, None]]: # Load the dataset. - with open(dataset_path) as f: + with open(dataset_path, encoding='utf-8') as f: dataset = json.load(f) # Filter out the conversations with less than 2 turns. 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'." # Load the dataset. - with open(dataset_path) as f: + with open(dataset_path, encoding='utf-8') as f: poem_lines = f.readlines() # Tokenize the poem lines. @@ -726,7 +726,7 @@ 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") as outfile: + with open(file_name, "w", encoding='utf-8') as outfile: json.dump(result_json, outfile)