[ { "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, "enable-diffusion-pipeline-profiler": true } }, "benchmark_params": [ { "name": "1024x1024_steps8", "dataset": "random", "task": "t2i", "width": 1024, "height": 1024, "num-inference-steps": 8, "num-prompts": 10, "max-concurrency": 1, "skip-performance-assertion": true, "baseline": { "throughput_qps": 0.213, "latency_mean": 4.6953, "latency_p99": 4.8601, "peak_memory_mb_max": 56912.0, "peak_memory_mb_mean": 56912.0 } } ] } ]