{
    "backend": {
        "name": "pytorch",
        "version": "2.2.1+cu118",
        "_target_": "optimum_benchmark.backends.pytorch.backend.PyTorchBackend",
        "model": "gpt2",
        "task": "text-generation",
        "library": "transformers",
        "device": "cuda",
        "device_ids": "0",
        "seed": 42,
        "inter_op_num_threads": null,
        "intra_op_num_threads": null,
        "hub_kwargs": {
            "revision": "main",
            "force_download": false,
            "local_files_only": false,
            "trust_remote_code": false
        },
        "no_weights": true,
        "device_map": null,
        "torch_dtype": null,
        "amp_autocast": false,
        "amp_dtype": null,
        "eval_mode": true,
        "to_bettertransformer": false,
        "low_cpu_mem_usage": null,
        "attn_implementation": null,
        "cache_implementation": null,
        "torch_compile": false,
        "torch_compile_config": {},
        "quantization_scheme": null,
        "quantization_config": {},
        "deepspeed_inference": false,
        "deepspeed_inference_config": {},
        "peft_type": null,
        "peft_config": {}
    },
    "launcher": {
        "name": "process",
        "_target_": "optimum_benchmark.launchers.process.launcher.ProcessLauncher",
        "device_isolation": false,
        "start_method": "spawn"
    },
    "benchmark": {
        "name": "inference",
        "_target_": "optimum_benchmark.benchmarks.inference.benchmark.InferenceBenchmark",
        "duration": 10,
        "warmup_runs": 10,
        "input_shapes": {
            "batch_size": 2,
            "num_choices": 2,
            "sequence_length": 16
        },
        "new_tokens": null,
        "energy": false,
        "memory": false,
        "latency": true,
        "forward_kwargs": {},
        "generate_kwargs": {},
        "call_kwargs": {}
    },
    "experiment_name": "test",
    "task": null,
    "model": null,
    "device": null,
    "library": null,
    "environment": {
        "cpu": " AMD EPYC 7742 64-Core Processor",
        "cpu_count": 128,
        "cpu_ram_mb": 540671.627264,
        "system": "Linux",
        "machine": "x86_64",
        "platform": "Linux-5.4.0-166-generic-x86_64-with-glibc2.35",
        "processor": "x86_64",
        "python_version": "3.10.12",
        "gpu": [
            "NVIDIA A100-SXM4-80GB",
            "NVIDIA A100-SXM4-80GB",
            "NVIDIA A100-SXM4-80GB",
            "NVIDIA DGX Display",
            "NVIDIA A100-SXM4-80GB"
        ],
        "gpu_count": 5,
        "gpu_vram_mb": 347892350976,
        "optimum_benchmark_version": "0.2.0",
        "optimum_benchmark_commit": "99c4ad891865d24ebb865cc853e21127a1872efe",
        "transformers_version": "4.38.2",
        "transformers_commit": null,
        "accelerate_version": "0.27.2",
        "accelerate_commit": null,
        "diffusers_version": null,
        "diffusers_commit": null,
        "optimum_version": null,
        "optimum_commit": null,
        "timm_version": null,
        "timm_commit": null,
        "peft_version": null,
        "peft_commit": null
    }
}