Files
vllm-omni/tests/perf/tests/benchmark_params.json
T

58 lines
1.7 KiB
JSON

[
{
"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": 0.001,
"latency_p99": 1000.0,
"peak_memory_mb_max": 400000,
"peak_memory_mb_mean": 400000
}
},
{
"name": "1536x1536_steps35",
"dataset": "random",
"task": "t2i",
"width": 1536,
"height": 1536,
"num-inference-steps": 35,
"num-prompts": 10,
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.001,
"latency_p99": 1000.0,
"peak_memory_mb_max": 400000,
"peak_memory_mb_mean": 400000
}
},
{
"name": "mixed_resolution",
"dataset": "random",
"task": "t2i",
"num-inference-steps": 20,
"num-prompts": 10,
"max-concurrency": 1,
"enable-negative-prompt": true,
"random-request-config": [
{"width": 512, "height": 512, "num_inference_steps": 20, "weight": 0.15},
{"width": 768, "height": 768, "num_inference_steps": 20, "weight": 0.25},
{"width": 1024, "height": 1024, "num_inference_steps": 25, "weight": 0.45},
{"width": 1536, "height": 1536, "num_inference_steps": 35, "weight": 0.15}
],
"baseline": {
"throughput_qps": 0.001,
"latency_p99": 1000.0,
"peak_memory_mb_max": 400000,
"peak_memory_mb_mean": 400000
}
}
]