Files
vllm-omni/tests/dfx/perf/tests/test_boogu_image_vllm_omni.json
T
2026-09-03 10:37:21 +08:00

82 lines
2.9 KiB
JSON

[
{
"test_name": "test_boogu_image_single_device",
"description": "Single-device baseline (no parallelism), concurrency sweep 1/2/4 at 512x512, 28 steps. Baselines recorded on 1x A40 46GB (measured c1/c2/c4: qps 0.0611/0.0609/0.0611, latency_mean 16.37/31.22/55.77 s, peak mem 36754 MB) with ~10% margin.",
"server_type": "vllm-omni",
"server_params": {
"model": "Boogu/Boogu-Image-0.1-Base",
"serve_args": {
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "512x512_steps28",
"dataset": "random",
"task": "t2i",
"width": 512,
"height": 512,
"num-inference-steps": 28,
"num-prompts": 10,
"max-concurrency": [1, 2, 4],
"warmup-requests": 4,
"warmup-concurrency": 4,
"warmup-num-inference-steps": 28,
"enable-negative-prompt": true,
"baseline": {
"H100": {
"throughput_qps": [0.0549, 0.0547, 0.0549],
"latency_mean": [18.0, 34.3, 61.4],
"peak_memory_mb_max": 40500,
"peak_memory_mb_mean": 40500
}
}
}
]
},
{
"test_name": "test_boogu_image_cfg_parallel_2",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": "H100"
},
"num_cards": 2
}
},
"full_model",
"diffusion"
],
"description": "Two-device CFG-parallel Base T2I measurement row. Run beside test_boogu_image_single_device on the same H100 revision and populate latency, throughput, speedup, and per-GPU peak-memory baselines from the resulting report.",
"server_type": "vllm-omni",
"server_params": {
"model": "Boogu/Boogu-Image-0.1-Base",
"serve_args": {
"cfg-parallel-size": 2,
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "512x512_steps28_cfg2",
"dataset": "random",
"task": "t2i",
"width": 512,
"height": 512,
"num-inference-steps": 28,
"num-prompts": 10,
"max-concurrency": 1,
"warmup-requests": 4,
"warmup-concurrency": 1,
"warmup-num-inference-steps": 28,
"enable-negative-prompt": true,
"extra-body": {
"guidance_scale": 4.0,
"seed": 42
}
}
]
}
]