[HunyuanImage][Perf] adapt to deploy config changes (#3996)

Signed-off-by: dengyunyang <584797741@qq.com>
This commit is contained in:
dengyunyang authored and GitHub committed 2026-05-30 14:48:50 +08:00
1 parent a3456752c5
commit 3b317285c4
4 files changed
+28 -88

No files matched your search

@@ -1,35 +1,33 @@
[
{
"test_name": "test_hunyuan_image_tp2_fp8_cfgp2",
"description": "TP=2 Quantization=fp8 CfgP=2 baseline",
"test_name": "test_hunyuan_image_tp2_cfgp2",
"description": "TP=2 CfgP=2 baseline",
"server_type": "vllm-omni",
"server_params": {
"model": "tencent/HunyuanImage-3.0-Instruct",
"serve_args": {
"deploy_config": "../vllm_omni/deploy/hunyuan_image3_dit.yaml",
"tensor-parallel-size": 2,
"cfg-parallel-size": 2,
"quantization": "fp8",
"distributed-executor-backend": "mp",
"enforce-eager": true,
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "1024x1024_steps50",
"name": "1024x1024_steps8",
"dataset": "random",
"task": "t2i",
"width": 1024,
"height": 1024,
"num-inference-steps": 50,
"num-inference-steps": 8,
"num-prompts": 10,
"max-concurrency": 1,
"skip-performance-assertion": true,
"baseline": {
"throughput_qps": 0.1035,
"latency_p99": 9.9057,
"peak_memory_mb_max": 66470,
"peak_memory_mb_mean": 66470
"throughput_qps": 0.21,
"latency_p99": 4.7469,
"peak_memory_mb_max": 101100,
"peak_memory_mb_mean": 101100
}
}
]
@@ -1,35 +1,33 @@
[
{
"test_name": "test_hunyuan_image_tp2_fp8_sp2",
"description": "TP=2 Quantization=fp8 SP=2 baseline",
"test_name": "test_hunyuan_image_tp2_sp2",
"description": "TP=2 SP=2 baseline",
"server_type": "vllm-omni",
"server_params": {
"model": "tencent/HunyuanImage-3.0-Instruct",
"serve_args": {
"deploy-config": "../vllm_omni/deploy/hunyuan_image3_dit.yaml",
"tensor-parallel-size": 2,
"usp": 2,
"quantization": "fp8",
"distributed-executor-backend": "mp",
"enforce-eager": true,
"ulysses-degree": 2,
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "1024x1024_steps50",
"name": "1024x1024_steps8",
"dataset": "random",
"task": "t2i",
"width": 1024,
"height": 1024,
"num-inference-steps": 50,
"num-inference-steps": 8,
"num-prompts": 10,
"max-concurrency": 1,
"skip-performance-assertion": true,
"baseline": {
"throughput_qps": 0.08,
"latency_p99": 12.0731,
"peak_memory_mb_max": 66314,
"peak_memory_mb_mean": 66314
"throughput_qps": 0.20,
"latency_p99": 5.1025,
"peak_memory_mb_max": 97402,
"peak_memory_mb_mean": 97402
}
}
]
@@ -1,34 +1,32 @@
[
{
"test_name": "test_hunyuan_image_tp4_fp8",
"description": "TP=4 Quantization=fp8 baseline",
"test_name": "test_hunyuan_image_tp4",
"description": "TP=4 baseline",
"server_type": "vllm-omni",
"server_params": {
"model": "tencent/HunyuanImage-3.0-Instruct",
"serve_args": {
"deploy-config": "../vllm_omni/deploy/hunyuan_image3_dit.yaml",
"tensor-parallel-size": 4,
"quantization": "fp8",
"distributed-executor-backend": "mp",
"enforce-eager": true,
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "1024x1024_steps50",
"name": "1024x1024_steps8",
"dataset": "random",
"task": "t2i",
"width": 1024,
"height": 1024,
"num-inference-steps": 50,
"num-inference-steps": 8,
"num-prompts": 10,
"max-concurrency": 1,
"skip-performance-assertion": true,
"baseline": {
"throughput_qps": 0.08,
"latency_p99": 13.1227,
"peak_memory_mb_max": 46838,
"peak_memory_mb_mean": 46838
"throughput_qps": 0.21,
"latency_p99": 4.9235,
"peak_memory_mb_max": 57576,
"peak_memory_mb_mean": 57576
}
}
]