Skip to content

[Perf] Add Performance Test for Qwen-Image Step-Level Execution #2707

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
Gaohan123 merged 4 commits into from
Apr 15, 2026
Merged

[Perf] Add Performance Test for Qwen-Image Step-Level Execution #2707

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b561f0b
test step-level execution
wtomin Apr 12, 2026
72e7128
Merge branch 'main' into test-step
wtomin Apr 15, 2026
3e88a93
Merge branch 'main' into test-step
wtomin Apr 15, 2026
2451cf1
Merge branch 'main' into test-step
Gaohan123 Apr 15, 2026
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
46 changes: 46 additions & 0 deletions tests/dfx/perf/tests/test_qwen_image_vllm_omni.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,52 @@
}
]
},
{
"test_name": "test_qwen_image_single_device_step_execution",
"description": "Single-device baseline (no parallelism) with step execution",
"server_type": "vllm-omni",
"server_params": {
"model": "Qwen/Qwen-Image",
"serve_args": {
"enable-diffusion-pipeline-profiler": true,
"step-execution": true
}
},
"benchmark_params": [
{
"name": "512x512_steps20",
"dataset": "random",
"task": "t2i",
"width": 512,
"height": 512,
"num-inference-steps": 20,
"num-prompts": 10,
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.30,
"latency_mean": 3.50,
"peak_memory_mb_mean": 67000
}
},
{
"name": "1536x1536_steps35",
"dataset": "random",
"task": "t2i",
"width": 1536,
Copy link
Copy Markdown
Collaborator

@gcanlin gcanlin Apr 12, 2026 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could we cover this issue #845 in the tests? Although it's a functional issue actually.

Copy link
Copy Markdown
Collaborator Author

@wtomin wtomin Apr 13, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It depends on whether we want to monitor its performance in the long run. I think currently, 1328x1328 is not our priority.

"height": 1536,
"num-inference-steps": 35,
"num-prompts": 10,
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.037,
"latency_mean": 27.0,
"peak_memory_mb_mean": 74000
}
}
]
},
{
"test_name": "test_qwen_image_ulysses2_cfg2_vae_patch4",
"description": "Ulysses SP=2 + CFG-parallel=2 + VAE Patch Parallel=4",
Expand Down
Loading