anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Test] Add performance tests for Qwen-Image-Layered model (#2807)

Browse Source 
Signed-off-by: John Liu BUAA <liukecheng97@gmail.com>
This commit is contained in:
John Liu BUAA authored and GitHub committed 2026-04-16 18:49:59 +08:00
1 parent f1cb4ebe4c
commit e8658b55d1
2 files changed
+52 -1
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

.buildkite/test-nightly.yml
+3 -1
View File
@@ -415,7 +415,9 @@ steps:
EXIT2=$$?
pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen_image_edit_2509_vllm_omni.json
EXIT3=$$?
if [ $$EXIT1 -eq 0 ] || [ $$EXIT2 -eq 0 ] || [ $$EXIT3 -eq 0 ]; then
pytest -s -v tests/dfx/perf/scripts/run_diffusion_benchmark.py --test-config-file tests/dfx/perf/tests/test_qwen_image_layered_vllm_omni.json
EXIT4=$$?
if [ $$EXIT1 -eq 0 ] || [ $$EXIT2 -eq 0 ] || [ $$EXIT3 -eq 0 ] || [ $$EXIT4 -eq 0 ]; then
buildkite-agent artifact upload "tests/dfx/perf/results/diffusion_result_*.json"
buildkite-agent artifact upload "tests/dfx/perf/results/logs/*.log"
fi
tests/dfx/perf/tests/test_qwen_image_layered_vllm_omni.json
+49
View File
@@ -0,0 +1,49 @@
[
{
"test_name": "test_qwen_image_layered_single_device",
"description": "Single-device baseline",
"server_type": "vllm-omni",
"server_params": {
"model": "Qwen/Qwen-Image-Layered",
"serve_args": {
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "640x640_steps20_i2i",
"dataset": "random",
"task": "i2i",
"width": 640,
"height": 640,
"num-inference-steps": 20,
"num-prompts": 10,
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.02,
"latency_mean": 40.0,
"peak_memory_mb_max": 70000,
"peak_memory_mb_mean": 70000
}
},
{
"name": "1024x1024_steps35_i2i",
"dataset": "random",
"task": "i2i",
"width": 1024,
"height": 1024,
"num-inference-steps": 35,
"num-prompts": 10,
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.005,
"latency_mean": 80.0,
"peak_memory_mb_max": 70000,
"peak_memory_mb_mean": 70000
}
}
]
}
]