[CI] Reduce Qwen-Image Function and share step-execution perf server (#6613)
Signed-off-by: NumberWan <wantszkin2003@gmail.com>
This commit is contained in:
1 parent
0d5d1115d6
commit
dd527b4245
2 files changed
+125
-177
No files matched your search
@@ -74,13 +74,14 @@
|
||||
"full_model",
|
||||
"diffusion"
|
||||
],
|
||||
"description": "Single-device baseline (no parallelism) with step execution",
|
||||
"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
|
||||
"step-execution": true,
|
||||
"max-num-seqs": 8
|
||||
}
|
||||
},
|
||||
"benchmark_params": [
|
||||
@@ -119,6 +120,27 @@
|
||||
"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]
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
@@ -243,53 +265,5 @@
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"test_name": "test_qwen_image_single_device_step_execution_high_concurrency",
|
||||
"mark": [
|
||||
{
|
||||
"hardware_marks": {
|
||||
"res": {
|
||||
"cuda": "H100"
|
||||
},
|
||||
"num_cards": 1
|
||||
}
|
||||
},
|
||||
"full_model",
|
||||
"diffusion"
|
||||
],
|
||||
"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": {
|
||||
"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]
|
||||
}
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
Reference in new issue
Block a user