[
    {
        "test_name": "llama8B_tp1_genai_perf",
        "qps_list": [4,8,16,32],
        "common_parameters": {
            "model": "meta-llama/Meta-Llama-3-8B-Instruct",
            "tp": 1,
            "port": 8000,
            "num_prompts": 500,
            "reuse_server": false
        },
        "vllm_server_parameters": {
            "disable_log_stats": "",
            "disable_log_requests": "",
            "gpu_memory_utilization": 0.9,
            "num_scheduler_steps": 10,
            "max_num_seqs": 512,
            "dtype": "bfloat16"
        },
        "genai_perf_input_parameters": {
        }
    }
]