Files
vllm-omni/tests/dfx/perf/tests/test_wan22_i2v_vllm_omni.json
T

133 lines
3.1 KiB
JSON

[
{
"test_name": "test_wan22_i2v_single_device",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": "H100"
},
"num_cards": 1
}
},
"full_model",
"diffusion"
],
"description": "Single-device baseline",
"server_type": "vllm-omni",
"server_params": {
"model": "Wan-AI/Wan2.2-I2V-A14B-Diffusers",
"serve_args": {
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "832x480_frames81_steps4",
"dataset": "random",
"task": "i2v",
"num-prompts": 10,
"max-concurrency": 1,
"num-input-images": 1,
"seed": 42,
"enable-negative-prompt": true,
"random-request-config": [
{
"width": 832,
"height": 480,
"num_inference_steps": 4,
"num_frames": 81,
"fps": 16,
"weight": 1
}
],
"baseline": {
"throughput_qps": 0.0434,
"latency_mean": 23.0654,
"peak_memory_mb_mean": 76360.0
}
}
]
},
{
"test_name": "test_wan22_i2v_usp2_vae_patch2_hsdp_slicing",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": "H100",
"npu": "A3"
},
"num_cards": 2
}
},
"full_model",
"diffusion"
],
"description": "USP=2 + VAE patch parallel=2 + HSDP + VAE slicing",
"server_type": "vllm-omni",
"server_params": {
"model": "Wan-AI/Wan2.2-I2V-A14B-Diffusers",
"serve_args": {
"usp": 2,
"vae-patch-parallel-size": 2,
"use-hsdp": true,
"vae-use-slicing": true,
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "832x480_frames81_steps4",
"dataset": "random",
"task": "i2v",
"num-prompts": 10,
"max-concurrency": 1,
"num-input-images": 1,
"seed": 42,
"enable-negative-prompt": true,
"random-request-config": [
{
"width": 832,
"height": 480,
"num_inference_steps": 4,
"num_frames": 81,
"fps": 16,
"weight": 1
}
],
"baseline": {
"throughput_qps": 0.0606,
"latency_mean": 16.4928,
"peak_memory_mb_mean": 47164.8
}
},
{
"name": "1280x720_frames121_steps4",
"dataset": "random",
"task": "i2v",
"num-prompts": 10,
"max-concurrency": 1,
"num-input-images": 1,
"seed": 42,
"enable-negative-prompt": true,
"random-request-config": [
{
"width": 1280,
"height": 720,
"num_inference_steps": 4,
"num_frames": 121,
"fps": 16,
"weight": 1
}
],
"baseline": {
"throughput_qps": 0.0124,
"latency_mean": 80.7784,
"peak_memory_mb_mean": 55374.3429
}
}
]
}
]