[
    {
        "test_name": "test_hunyuan_image3_ti2i_inline",
        "description": "AR (TP=2) + 2 * DiT (TP=2) - using inline dataset and deploy-config",
        "server_type": "vllm-omni",
        "benchmark_endpoint": "/v1/images/edits",
        "server_params": {
            "model": "tencent/HunyuanImage-3.0-Instruct",
            "serve_args": {
                "deploy-config-inline": {
                    "type": "yaml",
                    "content": {
                        "pipeline": "hunyuan_image_3_moe",
                        "async_chunk": false,
                        "trust_remote_code": true,
                        "connectors": {
                            "rdma_connector": {
                                "name": "MooncakeTransferEngineConnector",
                                "extra": {
                                    "host": "auto",
                                    "zmq_port": 50051,
                                    "protocol": "rdma",
                                    "device_name": "",
                                    "memory_pool_size": 17179869184,
                                    "memory_pool_device": "cpu"
                                }
                            }
                        },
                        "stages": [
                            {
                                "stage_id": 0,
                                "is_comprehension": true,
                                "final_output": true,
                                "final_output_type": "text",
                                "max_num_seqs": 16,
                                "gpu_memory_utilization": 0.95,
                                "enforce_eager": false,
                                "enable_prefix_caching": false,
                                "max_num_batched_tokens": 32768,
                                "devices": "0,1",
                                "tensor_parallel_size": 2,
                                "hf_overrides": {
                                    "rope_parameters": {
                                        "mrope_section": [0, 32, 32],
                                        "rope_type": "default"
                                    }
                                },
                                "omni_kv_config": {
                                    "need_send_cache": true
                                },
                                "output_connectors": {
                                    "to_stage_1": "rdma_connector"
                                },
                                "default_sampling_params": {
                                    "temperature": 0.0,
                                    "top_p": 1,
                                    "top_k": -1,
                                    "max_tokens": 8192,
                                    "detokenize": true,
                                    "skip_special_tokens": false,
                                    "stop_token_ids": [128025]
                                }
                            },
                            {
                                "stage_id": 1,
                                "max_num_seqs": 1,
                                "enforce_eager": true,
                                "devices": "2,3",
                                "distributed_executor_backend": "mp",
                                "omni_kv_config": {
                                    "need_recv_cache": true
                                },
                                "parallel_config": {
                                    "tensor_parallel_size": 2,
                                    "vae_patch_parallel_size": 2,
                                    "enable_expert_parallel": true
                                },
                                "input_connectors": {
                                    "from_stage_0": "rdma_connector"
                                },
                                "default_sampling_params": {
                                    "num_inference_steps": 50,
                                    "guidance_scale": 0
                                }
                            }
                        ],
                        "edges": [
                            {
                                "from": 0,
                                "to": 1,
                                "window_size": -1,
                                "max_inflight": 1
                            }
                        ]
                    }
                },
                "enable-diffusion-pipeline-profiler": true
            }
        },
        "benchmark_params": [
            {
                "name": "inline_dataset_5_requests",
                "dataset": "custom",
                "dataset-path-inline": {
                    "type": "jsonl",
                    "content": [
                        {
                            "prompt": "新年宠物海报，Q版圆润的可爱标题“新年快乐汪”，副标题“HAPPY NEW YEAR”。 鱼眼镜头，背景是房间门口，近景，上传的主体歪头笑，围着红色围巾，戴着红色毛线帽，高清，绒毛细节，面部特写。 宝丽莱相纸，超现实主义，写实主义，胶片摄影，打印颗粒感肌理。肌理，超写实，复古感。",
                            "image_urls": ["https://raw.githubusercontent.com/Tencent-Hunyuan/HunyuanImage-3.0/main/assets/demo_instruct_imgs/input_0_0.png"],
                            "num_inference_steps": 8,
                            "seed": 42,
                            "guidance_scale": 1.0
                        }
                    ]
                },
                "task": "ti2i",
                "bot-task": "think_recaption",
                "max-concurrency": 16,
                "num-prompts": 96,
                "skip-performance-assertion": true,
                "baseline": {
                    "throughput_qps": 0.1,
                    "latency_p99": 44.46,
                    "latency_mean": 35.57,
                    "latency_std_dev": 0.5,
                    "peak_memory_mb_max": 70000,
                    "peak_memory_mb_mean": 70000
                }
            }
        ]
    }
]