Signed-off-by: Didan Deng <33117903+wtomin@users.noreply.github.com> Signed-off-by: Gao Han <hgaoaf@connect.ust.hk> Co-authored-by: Gao Han <hgaoaf@connect.ust.hk>
220 lines
7.4 KiB
JSON
220 lines
7.4 KiB
JSON
[
|
|
{
|
|
"test_name": "test_qwen_image_single_device",
|
|
"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": {
|
|
"throughput_qps": 0.35,
|
|
"latency_mean": 3,
|
|
"peak_memory_mb_mean": 56000
|
|
}
|
|
},
|
|
{
|
|
"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": 0.03,
|
|
"latency_mean": 26,
|
|
"peak_memory_mb_mean": 65000
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"test_name": "test_qwen_image_single_device_step_execution",
|
|
"description": "Single-device baseline (no parallelism) with step execution",
|
|
"server_type": "vllm-omni",
|
|
"server_params": {
|
|
"model": "Qwen/Qwen-Image",
|
|
"serve_args": {
|
|
"enable-diffusion-pipeline-profiler": true,
|
|
"step-execution": 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": {
|
|
"throughput_qps": 0.35,
|
|
"latency_mean": 3,
|
|
"peak_memory_mb_mean": 56000
|
|
}
|
|
},
|
|
{
|
|
"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": 0.03,
|
|
"latency_mean": 26,
|
|
"peak_memory_mb_mean": 65000
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"test_name": "test_qwen_image_ulysses2_cfg2_vae_patch4",
|
|
"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": {
|
|
"throughput_qps": 0.11,
|
|
"latency_mean": 9,
|
|
"peak_memory_mb_mean": 55000
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"test_name": "test_qwen_image_ulysses2_cfg2_cache_dit",
|
|
"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": {
|
|
"throughput_qps": 0.46,
|
|
"latency_mean": 3,
|
|
"peak_memory_mb_mean": 56000
|
|
}
|
|
},
|
|
{
|
|
"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": 0.18,
|
|
"latency_mean": 6,
|
|
"peak_memory_mb_mean": 67000
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"test_name": "test_qwen_image_single_device_step_execution_high_concurrency",
|
|
"description": "Single-device Qwen-Image step-level execution benchmark at 512x512, 20 steps, concurrency sweep",
|
|
"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_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": {
|
|
"throughput_qps": [0.30, 0.50, 0.60, 0.70],
|
|
"latency_mean": [3.50, 4.00, 7.00, 12.00],
|
|
"peak_memory_mb_mean": [67000, 67000, 67000, 67000]
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|