[
    {
        "test_name": "serving_llama8B_tp1_sharegpt",
        "qps_list": [1, 4, 16, "inf"],
        "server_parameters": {
            "model": "meta-llama/Meta-Llama-3-8B",
            "tensor_parallel_size": 1,
            "swap_space": 16,
            "disable_log_stats": "",
            "disable_log_requests": "",
            "load_format": "dummy"
        },
        "client_parameters": {
            "model": "meta-llama/Meta-Llama-3-8B",
            "backend": "vllm",
            "dataset_name": "sharegpt",
            "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
            "num_prompts": 200
        }
    },
    {
        "test_name": "serving_llama70B_tp4_sharegpt",
        "qps_list": [1, 4, 16, "inf"],
        "server_parameters": {
            "model": "meta-llama/Meta-Llama-3-70B-Instruct",
            "tensor_parallel_size": 4,
            "swap_space": 16,
            "disable_log_stats": "",
            "disable_log_requests": "",
            "load_format": "dummy"
        },
        "client_parameters": {
            "model": "meta-llama/Meta-Llama-3-70B-Instruct",
            "backend": "vllm",
            "dataset_name": "sharegpt",
            "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
            "num_prompts": 200
        }
    },
    {
        "test_name": "serving_mixtral8x7B_tp2_sharegpt",
        "qps_list": [1, 4, 16, "inf"],
        "server_parameters": {
            "model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
            "tensor_parallel_size": 2,
            "swap_space": 16,
            "disable_log_stats": "",
            "disable_log_requests": "",
            "load_format": "dummy"
        },
        "client_parameters": {
            "model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
            "backend": "vllm",
            "dataset_name": "sharegpt",
            "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
            "num_prompts": 200
        }
    }
]