Files
vllm-omni/tests/dfx/perf/tests/test_bagel_vllm_omni.json
T
2026-05-28 09:41:46 +08:00

153 lines
4.4 KiB
JSON

[
{
"test_name": "test_bagel_single_device_single_stage_t2i",
"description": "Single-stage BAGEL (TP=1, CFG=1), t2i Task",
"server_type": "vllm-omni",
"server_params": {
"model": "ByteDance-Seed/BAGEL-7B-MoT",
"serve_args": {
"enable-diffusion-pipeline-profiler": true,
"deploy-config": "../vllm_omni/deploy/bagel_single_stage.yaml",
"no-async-chunk": true,
"tensor-parallel-size": 1,
"cfg-parallel-size": 1,
"gpu-memory-utilization": 0.90,
"max-model-len": 8192,
"max-num-batched-tokens": 9216
}
},
"benchmark_params": [
{
"name": "512x512_t2i_steps20",
"dataset": "random",
"task": "t2i",
"width": 512,
"height": 512,
"num-inference-steps": 20,
"num-prompts": 20,
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.3678,
"latency_mean": 2.691,
"peak_memory_mb_max": 33083.6,
"peak_memory_mb_mean": 33082.5
}
}
]
},
{
"test_name": "test_bagel_single_device_single_stage_i2i",
"description": "Single-stage BAGEL (TP=1, CFG=1), i2i Task",
"server_type": "vllm-omni",
"server_params": {
"model": "ByteDance-Seed/BAGEL-7B-MoT",
"serve_args": {
"enable-diffusion-pipeline-profiler": true,
"deploy-config": "../vllm_omni/deploy/bagel_single_stage.yaml",
"no-async-chunk": true,
"tensor-parallel-size": 1,
"cfg-parallel-size": 1,
"gpu-memory-utilization": 0.90,
"max-model-len": 8192,
"max-num-batched-tokens": 9216
}
},
"benchmark_params": [
{
"name": "512x512_i2i_steps20",
"dataset": "random",
"task": "i2i",
"width": 512,
"height": 512,
"num-inference-steps": 20,
"num-prompts": 20,
"max-concurrency": 1,
"enable-negative-prompt": true,
"num-input-images": 1,
"baseline": {
"throughput_qps": 0.3124,
"latency_mean": 3.1686,
"peak_memory_mb_max": 33448.8,
"peak_memory_mb_mean": 33447.7
}
}
]
},
{
"test_name": "test_bagel_single_device_multi_stage_t2i",
"description": "Two-stage BAGEL (bagel.yaml), TP=1, CFG=1, t2i Task",
"server_type": "vllm-omni",
"server_params": {
"model": "ByteDance-Seed/BAGEL-7B-MoT",
"serve_args": {
"enable-diffusion-pipeline-profiler": true,
"deploy-config": "../vllm_omni/deploy/bagel.yaml",
"no-async-chunk": true,
"tensor-parallel-size": 1,
"cfg-parallel-size": 1,
"gpu-memory-utilization": 0.45,
"max-model-len": 8192,
"max-num-batched-tokens": 9216
}
},
"benchmark_params": [
{
"name": "512x512_t2i_steps20",
"dataset": "random",
"task": "t2i",
"width": 512,
"height": 512,
"num-inference-steps": 20,
"num-prompts": 20,
"max-concurrency": 1,
"enable-negative-prompt": true,
"baseline": {
"throughput_qps": 0.3746,
"latency_mean": 2.6425,
"peak_memory_mb_max": 33077.0,
"peak_memory_mb_mean": 33077.0
}
}
]
},
{
"test_name": "test_bagel_single_device_multi_stage_i2i",
"description": "Two-stage BAGEL (bagel.yaml), TP=1, CFG=1, i2i Task",
"server_type": "vllm-omni",
"server_params": {
"model": "ByteDance-Seed/BAGEL-7B-MoT",
"serve_args": {
"enable-diffusion-pipeline-profiler": true,
"deploy-config": "../vllm_omni/deploy/bagel.yaml",
"no-async-chunk": true,
"tensor-parallel-size": 1,
"cfg-parallel-size": 1,
"gpu-memory-utilization": 0.45,
"max-model-len": 8192,
"max-num-batched-tokens": 9216
}
},
"benchmark_params": [
{
"name": "512x512_i2i_steps20",
"dataset": "random",
"task": "i2i",
"width": 512,
"height": 512,
"num-inference-steps": 20,
"num-prompts": 20,
"max-concurrency": 1,
"enable-negative-prompt": true,
"num-input-images": 1,
"baseline": {
"throughput_qps": 0.1349,
"latency_mean": 7.339,
"peak_memory_mb_max": 33321.2,
"peak_memory_mb_mean": 33321.2
}
}
]
}
]