throughput-tests-cpu.json

[
    {
        "test_name": "throughput_llama8B_tp2",
        "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
        },
        "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,
            "dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
            "num_prompts": 200,
            "backend": "vllm"
        }
    }
]