Skip to content
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.

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

[CI] Avoid naming different metrics with the same name in performance benchmark #5615

Merged
merged 3 commits into from
Jun 18, 2024
Merged
Changes from all commits
Commits
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
Original file line number Diff line number Diff line change
Expand Up @@ -15,10 +15,10 @@
"avg_latency": "Mean latency (ms)",
# "P10": "P10 (s)",
# "P25": "P25 (s)",
"P50": "Median",
"P50": "Median latency (ms)",
# "P75": "P75 (s)",
# "P90": "P90 (s)",
"P99": "P99",
"P99": "P99 latency (ms)",
}

# thoughput tests and the keys that will be printed into markdown
Expand All @@ -43,15 +43,14 @@
# "input_throughput": "Input Tput (tok/s)",
# "output_throughput": "Output Tput (tok/s)",
"mean_ttft_ms": "Mean TTFT (ms)",
# do not say TTFT again to avoid the table getting too wide
"median_ttft_ms": "Median",
"p99_ttft_ms": "P99",
"median_ttft_ms": "Median TTFT (ms)",
"p99_ttft_ms": "P99 TTFT (ms)",
# "mean_tpot_ms": "Mean TPOT (ms)",
# "median_tpot_ms": "Median",
# "p99_tpot_ms": "P99",
"mean_itl_ms": "Mean ITL (ms)",
"median_itl_ms": "Median",
"p99_itl_ms": "P99",
"median_itl_ms": "Median ITL (ms)",
"p99_itl_ms": "P99 ITL (ms)",
}


Expand Down Expand Up @@ -183,3 +182,11 @@ def results_to_json(latency, throughput, serving):
serving_tests_markdown_table=serving_md_table,
benchmarking_results_in_json_string=processed_results_json)
f.write(results)

# document benchmarking results in json
with open(results_folder / "benchmark_results.json", "w") as f:

results = latency_results.to_dict(
orient='records') + throughput_results.to_dict(
orient='records') + serving_results.to_dict(orient='records')
f.write(json.dumps(results))
Loading