Skip to content

[QoL] Add generated text summary to top of output file #116

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
Aug 27, 2025
Merged

[QoL] Add generated text summary to top of output file #116

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c482ce2
add generated text summary to output file
benchislett Aug 27, 2025
9846648
lint
benchislett Aug 27, 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
2 changes: 1 addition & 1 deletion src/flexible_inference_benchmark/engine/data.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -308,7 +308,7 @@ def __init__(
filtered_dataset = [
(prompt_str, prompt_len, output_len)
for prompt_str, prompt_len, output_len in tokenized_dataset
if (prompt_len > 4 and output_len > 4)
if (prompt_len > 4 and output_len > 0)
]

self.data = filtered_dataset
Expand Down
5 changes: 5 additions & 0 deletions src/flexible_inference_benchmark/main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -927,9 +927,14 @@ def run_main(args: argparse.Namespace) -> None:
output_list: List[Any] = send_requests(client, requests_prompts, requests_times, arr_dims)
benchmark_time = time.perf_counter() - t
# pylint: disable=line-too-long

text_summaries: list[str] = []
if any(hasattr(o, "generated_text") for o in output_list):
text_summaries = [o.generated_text for o in output_list if hasattr(o, "generated_text")] # type: ignore
output = {
"backend": args.backend,
"time": benchmark_time,
"summary": text_summaries,
"outputs": [request_func_output.model_dump() for request_func_output in output_list], # type: ignore
"inputs": requests_prompts,
"tokenizer": args.tokenizer if args.tokenizer else args.model,
Expand Down
Loading