biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Convert .buildkite to ruff format (#17656)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor
2025-05-13 10:28:31 +01:00
committed by GitHub
parent 23b3134eb5
commit 98fcba1575
11 changed files with 182 additions and 114 deletions
Download Patch File Download Diff File Expand all files Collapse all files

89
.buildkite/nightly-benchmarks/scripts/convert-results-json-to-markdown.py
View File

@@ -65,18 +65,18 @@ def read_markdown(file):
def results_to_json(latency, throughput, serving):
return json.dumps({
'latency': latency.to_dict(),
'throughput': throughput.to_dict(),
'serving': serving.to_dict()
})
return json.dumps(
{
"latency": latency.to_dict(),
"throughput": throughput.to_dict(),
"serving": serving.to_dict(),
}
)
if __name__ == "__main__":
# collect results
for test_file in results_folder.glob("*.json"):
with open(test_file) as f:
raw_result = json.loads(f.read())
@@ -120,7 +120,8 @@ if __name__ == "__main__":
for perc in [10, 25, 50, 75, 90, 99]:
# Multiply 1000 to convert the time unit from s to ms
raw_result.update(
{f"P{perc}": 1000 * raw_result["percentiles"][str(perc)]})
{f"P{perc}": 1000 * raw_result["percentiles"][str(perc)]}
)
raw_result["avg_latency"] = raw_result["avg_latency"] * 1000
# add the result to raw_result
@@ -153,26 +154,27 @@ if __name__ == "__main__":
serving_results = pd.DataFrame.from_dict(serving_results)
throughput_results = pd.DataFrame.from_dict(throughput_results)
raw_results_json = results_to_json(latency_results, throughput_results,
serving_results)
raw_results_json = results_to_json(
latency_results, throughput_results, serving_results
)
# remapping the key, for visualization purpose
if not latency_results.empty:
latency_results = latency_results[list(
latency_column_mapping.keys())].rename(
columns=latency_column_mapping)
latency_results = latency_results[list(latency_column_mapping.keys())].rename(
columns=latency_column_mapping
)
if not serving_results.empty:
serving_results = serving_results[list(
serving_column_mapping.keys())].rename(
columns=serving_column_mapping)
serving_results = serving_results[list(serving_column_mapping.keys())].rename(
columns=serving_column_mapping
)
if not throughput_results.empty:
throughput_results = throughput_results[list(
throughput_results_column_mapping.keys())].rename(
columns=throughput_results_column_mapping)
throughput_results = throughput_results[
list(throughput_results_column_mapping.keys())
].rename(columns=throughput_results_column_mapping)
processed_results_json = results_to_json(latency_results,
throughput_results,
serving_results)
processed_results_json = results_to_json(
latency_results, throughput_results, serving_results
)
for df in [latency_results, serving_results, throughput_results]:
if df.empty:
@@ -184,38 +186,39 @@ if __name__ == "__main__":
# The GPUs sometimes come in format of "GPUTYPE\nGPUTYPE\n...",
# we want to turn it into "8xGPUTYPE"
df["GPU"] = df["GPU"].apply(
lambda x: f"{len(x.split('\n'))}x{x.split('\n')[0]}")
lambda x: f"{len(x.split('\n'))}x{x.split('\n')[0]}"
)
# get markdown tables
latency_md_table = tabulate(latency_results,
headers='keys',
tablefmt='pipe',
showindex=False)
serving_md_table = tabulate(serving_results,
headers='keys',
tablefmt='pipe',
showindex=False)
throughput_md_table = tabulate(throughput_results,
headers='keys',
tablefmt='pipe',
showindex=False)
latency_md_table = tabulate(
latency_results, headers="keys", tablefmt="pipe", showindex=False
)
serving_md_table = tabulate(
serving_results, headers="keys", tablefmt="pipe", showindex=False
)
throughput_md_table = tabulate(
throughput_results, headers="keys", tablefmt="pipe", showindex=False
)
# document the result
with open(results_folder / "benchmark_results.md", "w") as f:
results = read_markdown("../.buildkite/nightly-benchmarks/" +
"performance-benchmarks-descriptions.md")
results = read_markdown(
"../.buildkite/nightly-benchmarks/"
+ "performance-benchmarks-descriptions.md"
)
results = results.format(
latency_tests_markdown_table=latency_md_table,
throughput_tests_markdown_table=throughput_md_table,
serving_tests_markdown_table=serving_md_table,
benchmarking_results_in_json_string=processed_results_json)
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')
results = (
latency_results.to_dict(orient="records")
+ throughput_results.to_dict(orient="records")
+ serving_results.to_dict(orient="records")
)
f.write(json.dumps(results))

15
.buildkite/nightly-benchmarks/scripts/download-tokenizer.py
View File

@@ -14,15 +14,12 @@ def main(model, cachedir):
if __name__ == "__main__":
parser = argparse.ArgumentParser(
description="Download and save Hugging Face tokenizer")
parser.add_argument("--model",
type=str,
required=True,
help="Name of the model")
parser.add_argument("--cachedir",
type=str,
required=True,
help="Directory to save the tokenizer")
description="Download and save Hugging Face tokenizer"
)
parser.add_argument("--model", type=str, required=True, help="Name of the model")
parser.add_argument(
"--cachedir", type=str, required=True, help="Directory to save the tokenizer"
)
args = parser.parse_args()
main(args.model, args.cachedir)

41
.buildkite/nightly-benchmarks/scripts/generate-nightly-markdown.py
View File

@@ -11,33 +11,33 @@ from tabulate import tabulate
def parse_arguments():
parser = argparse.ArgumentParser(
description=
'Parse command line arguments for summary-nightly-results script.')
parser.add_argument('--results-folder',
type=str,
required=True,
help='The folder where the results are stored.')
parser.add_argument('--description',
type=str,
required=True,
help='Description of the results.')
description="Parse command line arguments for summary-nightly-results script."
)
parser.add_argument(
"--results-folder",
type=str,
required=True,
help="The folder where the results are stored.",
)
parser.add_argument(
"--description", type=str, required=True, help="Description of the results."
)
args = parser.parse_args()
return args
def get_perf(df, method, model, metric):
means = []
for qps in [2, 4, 8, 16, "inf"]:
target = df['Test name'].str.contains(model)
target = target & df['Engine'].str.contains(method)
target = target & df['Test name'].str.contains("qps_" + str(qps))
target = df["Test name"].str.contains(model)
target = target & df["Engine"].str.contains(method)
target = target & df["Test name"].str.contains("qps_" + str(qps))
filtered_df = df[target]
if filtered_df.empty:
means.append(0.)
means.append(0.0)
else:
means.append(filtered_df[metric].values[0])
@@ -45,7 +45,6 @@ def get_perf(df, method, model, metric):
def get_perf_w_std(df, method, model, metric):
if metric in ["TTFT", "ITL"]:
mean = get_perf(df, method, model, "Mean " + metric + " (ms)")
mean = mean.tolist()
@@ -60,7 +59,8 @@ def get_perf_w_std(df, method, model, metric):
else:
assert metric == "Tput"
mean = get_perf(df, method, model, "Input Tput (tok/s)") + get_perf(
df, method, model, "Output Tput (tok/s)")
df, method, model, "Output Tput (tok/s)"
)
mean = mean.tolist()
std = None
@@ -80,18 +80,17 @@ def main(args):
# generate markdown table
df = pd.DataFrame.from_dict(results)
md_table = tabulate(df, headers='keys', tablefmt='pipe', showindex=False)
md_table = tabulate(df, headers="keys", tablefmt="pipe", showindex=False)
with open(args.description) as f:
description = f.read()
description = description.format(
nightly_results_benchmarking_table=md_table)
description = description.format(nightly_results_benchmarking_table=md_table)
with open("nightly_results.md", "w") as f:
f.write(description)
if __name__ == '__main__':
if __name__ == "__main__":
args = parse_arguments()
main(args)

24
.buildkite/nightly-benchmarks/scripts/summary-nightly-results.py
View File

@@ -34,10 +34,8 @@ serving_column_mapping = {
}
if __name__ == "__main__":
# collect results
for test_file in results_folder.glob("*.json"):
with open(test_file) as f:
raw_result = json.loads(f.read())
@@ -56,17 +54,16 @@ if __name__ == "__main__":
serving_results = pd.DataFrame.from_dict(serving_results)
if not serving_results.empty:
serving_results = serving_results[list(
serving_column_mapping.keys())].rename(
columns=serving_column_mapping)
serving_results = serving_results[list(serving_column_mapping.keys())].rename(
columns=serving_column_mapping
)
serving_md_table_with_headers = tabulate(serving_results,
headers='keys',
tablefmt='pipe',
showindex=False)
serving_md_table_with_headers = tabulate(
serving_results, headers="keys", tablefmt="pipe", showindex=False
)
# remove the first line of header
serving_md_table_lines = serving_md_table_with_headers.split('\n')
serving_md_table_without_header = '\n'.join(serving_md_table_lines[2:])
serving_md_table_lines = serving_md_table_with_headers.split("\n")
serving_md_table_without_header = "\n".join(serving_md_table_lines[2:])
prefix = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
prefix = prefix + "_" + os.environ.get("CURRENT_LLM_SERVING_ENGINE")
@@ -76,10 +73,9 @@ if __name__ == "__main__":
# document results with header.
# for those who wants to reproduce our benchmark.
f.write(serving_md_table_with_headers)
f.write('\n')
f.write("\n")
# document benchmarking results in json
with open(results_folder / f"{prefix}_nightly_results.json", "w") as f:
results = serving_results.to_dict(orient='records')
results = serving_results.to_dict(orient="records")
f.write(json.dumps(results))