serving-tests-cpu.json

[
    {
        "test_name": "serving_llama8B_tp1_sharegpt",
        "qps_list": [1, 4, 16, "inf"],
        "max_concurrency_list": [32],
        "server_environment_variables": {
            "VLLM_RPC_TIMEOUT": 100000,
	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
	    "VLLM_CPU_SGL_KERNEL": 1,
	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "server_parameters": {
            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "tensor_parallel_size": 1,
	    "dtype": "bfloat16",
	    "distributed_executor_backend": "mp",
	    "block_size": 128,
	    "trust_remote_code": "",
            "disable_log_stats": "",
	    "enforce_eager": "",
	    "max_num_batched_tokens": 2048,
	    "max_num_seqs": 256,
            "load_format": "dummy"
        },
        "client_parameters": {
            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "backend": "vllm",
            "dataset_name": "sharegpt",
            "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
            "num_prompts": 32
        }
    },
    {
        "test_name": "serving_llama8B_tp2_sharegpt",
        "qps_list": [1, 4, 16, "inf"],
        "max_concurrency_list": [32],
        "server_environment_variables": {
            "VLLM_RPC_TIMEOUT": 100000,
	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
	    "VLLM_CPU_SGL_KERNEL": 1,
	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "server_parameters": {
            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "tensor_parallel_size": 2,
	    "dtype": "bfloat16",
	    "distributed_executor_backend": "mp",
	    "block_size": 128,
	    "trust_remote_code": "",
            "disable_log_stats": "",
	    "enforce_eager": "",
	    "max_num_batched_tokens": 2048,
	    "max_num_seqs": 256,
            "load_format": "dummy"
        },
        "client_parameters": {
            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "backend": "vllm",
            "dataset_name": "sharegpt",
            "dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
            "num_prompts": 32
        }
    },
    {
        "test_name": "serving_llama8B_tp1_random_128_128",
        "qps_list": [1, 4, 16, "inf"],
        "max_concurrency_list": [32],
        "server_environment_variables": {
            "VLLM_RPC_TIMEOUT": 100000,
	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
	    "VLLM_CPU_SGL_KERNEL": 1,
	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "server_parameters": {
            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "tensor_parallel_size": 1,
	    "dtype": "bfloat16",
	    "distributed_executor_backend": "mp",
	    "block_size": 128,
	    "trust_remote_code": "",
	    "enable_chunked_prefill": "",
            "disable_log_stats": "",
	    "enforce_eager": "",
	    "max_num_batched_tokens": 2048,
	    "max_num_seqs": 256,
            "load_format": "dummy"
        },
        "client_parameters": {
            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "backend": "vllm",
            "dataset_name": "random",
	    "random-input-len": 128,
	    "random-output-len": 128,
	    "ignore-eos": "",
            "num_prompts": 32
        }
    },
    {
        "test_name": "serving_llama8B_tp2_random_128_128",
        "qps_list": [1, 4, 16, "inf"],
        "max_concurrency_list": [32],
        "server_environment_variables": {
            "VLLM_RPC_TIMEOUT": 100000,
	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
	    "VLLM_CPU_SGL_KERNEL": 1,
	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "server_parameters": {
            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "tensor_parallel_size": 2,
	    "dtype": "bfloat16",
	    "distributed_executor_backend": "mp",
	    "block_size": 128,
	    "trust_remote_code": "",
	    "enable_chunked_prefill": "",
            "disable_log_stats": "",
	    "enforce_eager": "",
	    "max_num_batched_tokens": 2048,
	    "max_num_seqs": 256,
            "load_format": "dummy"
        },
        "client_parameters": {
            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "backend": "vllm",
            "dataset_name": "random",
	    "random-input-len": 128,
	    "random-output-len": 128,
	    "ignore-eos": "",
            "num_prompts": 32
        }
    },
    {
        "test_name": "serving_llama8B_tp1_random_128_2048",
        "qps_list": [1, 4, 16, "inf"],
        "max_concurrency_list": [32],
        "server_environment_variables": {
            "VLLM_RPC_TIMEOUT": 100000,
	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
	    "VLLM_CPU_SGL_KERNEL": 1,
	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "server_parameters": {
            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "tensor_parallel_size": 1,
	    "dtype": "bfloat16",
	    "distributed_executor_backend": "mp",
	    "block_size": 128,
	    "trust_remote_code": "",
	    "enable_chunked_prefill": "",
            "disable_log_stats": "",
	    "enforce_eager": "",
	    "max_num_batched_tokens": 2048,
	    "max_num_seqs": 256,
            "load_format": "dummy"
        },
        "client_parameters": {
            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "backend": "vllm",
            "dataset_name": "random",
	    "random-input-len": 128,
	    "random-output-len": 2048,
	    "ignore-eos": "",
            "num_prompts": 32
        }
    },
    {
        "test_name": "serving_llama8B_tp2_random_128_2048",
        "qps_list": [1, 4, 16, "inf"],
        "max_concurrency_list": [32],
        "server_environment_variables": {
            "VLLM_RPC_TIMEOUT": 100000,
	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
	    "VLLM_CPU_SGL_KERNEL": 1,
	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "server_parameters": {
            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "tensor_parallel_size": 2,
	    "dtype": "bfloat16",
	    "distributed_executor_backend": "mp",
	    "block_size": 128,
	    "trust_remote_code": "",
	    "enable_chunked_prefill": "",
            "disable_log_stats": "",
	    "enforce_eager": "",
	    "max_num_batched_tokens": 2048,
	    "max_num_seqs": 256,
            "load_format": "dummy"
        },
        "client_parameters": {
            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "backend": "vllm",
            "dataset_name": "random",
	    "random-input-len": 128,
	    "random-output-len": 2048,
	    "ignore-eos": "",
            "num_prompts": 32
        }
    },
    {
        "test_name": "serving_llama8B_tp1_random_2048_128",
        "qps_list": [1, 4, 16, "inf"],
        "max_concurrency_list": [32],
        "server_environment_variables": {
            "VLLM_RPC_TIMEOUT": 100000,
	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
	    "VLLM_CPU_SGL_KERNEL": 1,
	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "server_parameters": {
            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "tensor_parallel_size": 1,
	    "dtype": "bfloat16",
	    "distributed_executor_backend": "mp",
	    "block_size": 128,
	    "trust_remote_code": "",
	    "enable_chunked_prefill": "",
            "disable_log_stats": "",
	    "enforce_eager": "",
	    "max_num_batched_tokens": 2048,
	    "max_num_seqs": 256,
            "load_format": "dummy"
        },
        "client_parameters": {
            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "backend": "vllm",
            "dataset_name": "random",
	    "random-input-len": 2048,
	    "random-output-len": 128,
	    "ignore-eos": "",
            "num_prompts": 32
        }
    },
    {
        "test_name": "serving_llama8B_tp2_random_2048_128",
        "qps_list": [1, 4, 16, "inf"],
        "max_concurrency_list": [32],
        "server_environment_variables": {
            "VLLM_RPC_TIMEOUT": 100000,
	    "VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
	    "VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
	    "VLLM_CPU_SGL_KERNEL": 1,
	    "VLLM_CPU_KVCACHE_SPACE": 40
        },
        "server_parameters": {
            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "tensor_parallel_size": 2,
	    "dtype": "bfloat16",
	    "distributed_executor_backend": "mp",
	    "block_size": 128,
	    "trust_remote_code": "",
	    "enable_chunked_prefill": "",
            "disable_log_stats": "",
	    "enforce_eager": "",
	    "max_num_batched_tokens": 2048,
	    "max_num_seqs": 256,
            "load_format": "dummy"
        },
        "client_parameters": {
            "model": "meta-llama/Llama-3.1-8B-Instruct",
            "backend": "vllm",
            "dataset_name": "random",
	    "random-input-len": 2048,
	    "random-output-len": 128,
	    "ignore-eos": "",
            "num_prompts": 32
        }
    }
]