270 lines
6.7 KiB
JSON
270 lines
6.7 KiB
JSON
[
|
|
{
|
|
"test_name": "test_qwen_image_single_device",
|
|
"mark": [
|
|
{
|
|
"hardware_marks": {
|
|
"res": {
|
|
"cuda": "H100"
|
|
},
|
|
"num_cards": 1
|
|
}
|
|
},
|
|
"full_model",
|
|
"diffusion"
|
|
],
|
|
"description": "Single-device baseline (no parallelism)",
|
|
"server_type": "vllm-omni",
|
|
"server_params": {
|
|
"model": "Qwen/Qwen-Image",
|
|
"serve_args": {
|
|
"enable-diffusion-pipeline-profiler": 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": {
|
|
"H100": {
|
|
"throughput_qps": 0.4153,
|
|
"latency_mean": 2.4065,
|
|
"peak_memory_mb_mean": 55062.0
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"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": {
|
|
"H100": {
|
|
"throughput_qps": 0.0423,
|
|
"latency_mean": 23.5991,
|
|
"peak_memory_mb_mean": 64546.0
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"test_name": "test_qwen_image_single_device_step_execution",
|
|
"mark": [
|
|
{
|
|
"hardware_marks": {
|
|
"res": {
|
|
"cuda": "H100"
|
|
},
|
|
"num_cards": 1
|
|
}
|
|
},
|
|
"full_model",
|
|
"diffusion"
|
|
],
|
|
"description": "Single-device step execution: sequential 512/1536 plus 512 concurrency sweep. One server (max-num-seqs 8).",
|
|
"server_type": "vllm-omni",
|
|
"server_params": {
|
|
"model": "Qwen/Qwen-Image",
|
|
"serve_args": {
|
|
"enable-diffusion-pipeline-profiler": true,
|
|
"step-execution": true,
|
|
"max-num-seqs": 8
|
|
}
|
|
},
|
|
"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": {
|
|
"H100": {
|
|
"throughput_qps": 0.4175,
|
|
"latency_mean": 2.3953,
|
|
"peak_memory_mb_mean": 54952.0
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"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": {
|
|
"H100": {
|
|
"throughput_qps": 0.0423,
|
|
"latency_mean": 23.5768,
|
|
"peak_memory_mb_mean": 64500.0
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"name": "512x512_steps20_high_concurrency",
|
|
"dataset": "random",
|
|
"task": "t2i",
|
|
"width": 512,
|
|
"height": 512,
|
|
"num-inference-steps": 20,
|
|
"num-prompts": [20, 40, 80, 160],
|
|
"max-concurrency": [1, 2, 4, 8],
|
|
"warmup-requests": 8,
|
|
"warmup-concurrency": 8,
|
|
"warmup-num-inference-steps": 20,
|
|
"enable-negative-prompt": true,
|
|
"baseline": {
|
|
"H100": {
|
|
"throughput_qps": [0.3937, 0.6606, 0.6188, 0.7752],
|
|
"latency_mean": [2.5466, 3.0235, 6.3948, 10.1944],
|
|
"peak_memory_mb_mean": [55149.0, 55150.0, 55153.1458, 55156.325]
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"test_name": "test_qwen_image_ulysses2_cfg2_vae_patch4",
|
|
"mark": [
|
|
{
|
|
"hardware_marks": {
|
|
"res": {
|
|
"cuda": "H100"
|
|
},
|
|
"num_cards": 4
|
|
}
|
|
},
|
|
"full_model",
|
|
"diffusion"
|
|
],
|
|
"description": "Ulysses SP=2 + CFG-parallel=2 + VAE Patch Parallel=4",
|
|
"server_type": "vllm-omni",
|
|
"server_params": {
|
|
"model": "Qwen/Qwen-Image",
|
|
"serve_args": {
|
|
"ulysses-degree": 2,
|
|
"cfg-parallel-size": 2,
|
|
"vae-patch-parallel-size": 4,
|
|
"vae-use-tiling": true,
|
|
"enable-diffusion-pipeline-profiler": true
|
|
}
|
|
},
|
|
"benchmark_params": [
|
|
{
|
|
"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": {
|
|
"H100": {
|
|
"throughput_qps": 0.1214,
|
|
"latency_mean": 8.2211,
|
|
"peak_memory_mb_mean": 54474.0
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"test_name": "test_qwen_image_ulysses2_cfg2_cache_dit",
|
|
"mark": [
|
|
{
|
|
"hardware_marks": {
|
|
"res": {
|
|
"cuda": "H100"
|
|
},
|
|
"num_cards": 4
|
|
}
|
|
},
|
|
"full_model",
|
|
"diffusion"
|
|
],
|
|
"description": "Ulysses SP=2 + CFG-parallel=2 + CacheDiT acceleration",
|
|
"server_type": "vllm-omni",
|
|
"server_params": {
|
|
"model": "Qwen/Qwen-Image",
|
|
"serve_args": {
|
|
"ulysses-degree": 2,
|
|
"cfg-parallel-size": 2,
|
|
"cache-backend": "cache_dit",
|
|
"cache-config": {
|
|
"Fn_compute_blocks": 1,
|
|
"Bn_compute_blocks": 0,
|
|
"max_warmup_steps": 4,
|
|
"residual_diff_threshold": 0.24,
|
|
"max_continuous_cached_steps": 3,
|
|
"enable_taylorseer": false,
|
|
"taylorseer_order": 1,
|
|
"scm_steps_mask_policy": null,
|
|
"scm_steps_policy": "dynamic"
|
|
},
|
|
"enable-diffusion-pipeline-profiler": 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": {
|
|
"H100": {
|
|
"throughput_qps": 0.559,
|
|
"latency_mean": 1.794,
|
|
"peak_memory_mb_mean": 55174.0
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"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": {
|
|
"H100": {
|
|
"throughput_qps": 0.1918,
|
|
"latency_mean": 5.2022,
|
|
"peak_memory_mb_mean": 64750.0
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|