Skip to content

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

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 3 commits into from
Jun 18, 2024
Merged

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

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4548d33
Avoid naming different metrics with the same name
KuntaiDu Jun 18, 2024
522b1dd
add benchmark_results.json artifact
KuntaiDu Jun 18, 2024
5029f40
make ruff happy
KuntaiDu Jun 18, 2024
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
21 changes: 14 additions & 7 deletions .buildkite/nightly-benchmarks/scripts/convert-results-json-to-markdown.py
View file
Open in desktop
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))