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

Fix some issues with benchmark data output (#13641)

Browse Source 
Signed-off-by: Huy Do <huydhn@gmail.com>
This commit is contained in:
Huy Do
2025-02-23 18:23:18 -08:00
committed by GitHub
parent cbae7af552
commit e7ef74e26e
7 changed files with 61 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
.buildkite/nightly-benchmarks/scripts/convert-results-json-to-markdown.py
View File

@@ -84,8 +84,13 @@ if __name__ == "__main__":
# this result is generated via `benchmark_serving.py`
# attach the benchmarking command to raw_result
with open(test_file.with_suffix(".commands")) as f:
command = json.loads(f.read())
try:
with open(test_file.with_suffix(".commands")) as f:
command = json.loads(f.read())
except OSError as e:
print(e)
continue
raw_result.update(command)
# update the test name of this result
@@ -99,8 +104,13 @@ if __name__ == "__main__":
# this result is generated via `benchmark_latency.py`
# attach the benchmarking command to raw_result
with open(test_file.with_suffix(".commands")) as f:
command = json.loads(f.read())
try:
with open(test_file.with_suffix(".commands")) as f:
command = json.loads(f.read())
except OSError as e:
print(e)
continue
raw_result.update(command)
# update the test name of this result
@@ -121,8 +131,13 @@ if __name__ == "__main__":
# this result is generated via `benchmark_throughput.py`
# attach the benchmarking command to raw_result
with open(test_file.with_suffix(".commands")) as f:
command = json.loads(f.read())
try:
with open(test_file.with_suffix(".commands")) as f:
command = json.loads(f.read())
except OSError as e:
print(e)
continue
raw_result.update(command)
# update the test name of this result

3
.buildkite/nightly-benchmarks/scripts/run-performance-benchmarks.sh
View File

@@ -309,11 +309,14 @@ run_serving_tests() {
new_test_name=$test_name"_qps_"$qps
# pass the tensor parallel size to the client so that it can be displayed
# on the benchmark dashboard
client_command="python3 benchmark_serving.py \
--save-result \
--result-dir $RESULTS_FOLDER \
--result-filename ${new_test_name}.json \
--request-rate $qps \
--metadata "tensor_parallel_size=$tp" \
$client_args"
echo "Running test case $test_name with qps $qps"