58 lines
1.4 KiB
JSON
58 lines
1.4 KiB
JSON
[
|
|
{
|
|
"test_name": "test_hunyuan_image_tp2_cfgp2",
|
|
"mark": [
|
|
{
|
|
"hardware_marks": {
|
|
"res": {
|
|
"cuda": "H100",
|
|
"npu": "A3"
|
|
},
|
|
"num_cards": 4
|
|
}
|
|
},
|
|
"diffusion",
|
|
"local_model"
|
|
],
|
|
"description": "TP=2 CfgP=2 baseline",
|
|
"server_type": "vllm-omni",
|
|
"server_params": {
|
|
"model": "tencent/HunyuanImage-3.0-Instruct",
|
|
"serve_args": {
|
|
"deploy_config": "../vllm_omni/deploy/hunyuan_image3_dit.yaml",
|
|
"tensor-parallel-size": 2,
|
|
"cfg-parallel-size": 2,
|
|
"vae-patch-parallel-size": 4,
|
|
"vae-use-tiling": true,
|
|
"enable-diffusion-pipeline-profiler": true
|
|
}
|
|
},
|
|
"benchmark_params": [
|
|
{
|
|
"name": "1024x1024_steps8",
|
|
"dataset": "random",
|
|
"task": "t2i",
|
|
"width": 1024,
|
|
"height": 1024,
|
|
"num-inference-steps": 8,
|
|
"num-prompts": 10,
|
|
"max-concurrency": 1,
|
|
"baseline": {
|
|
"H200": {
|
|
"throughput_qps": 0.21,
|
|
"latency_p99": 4.7469,
|
|
"peak_memory_mb_max": 101100,
|
|
"peak_memory_mb_mean": 101100
|
|
},
|
|
"A3": {
|
|
"throughput_qps": 0.1855,
|
|
"latency_p99": 5.6304,
|
|
"peak_memory_mb_max": 47194.0,
|
|
"peak_memory_mb_mean": 47194.0
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|