{
    "backend": {
        "name": "pytorch",
        "version": "2.1.2",
        "_target_": "optimum_benchmark.backends.pytorch.backend.PyTorchBackend",
        "model": "LLMNewbie/vic_critP_20pr",
        "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": "torchrun",
        "_target_": "optimum_benchmark.launchers.torchrun.launcher.TorchrunLauncher",
        "device_isolation": false,
        "min_nodes": 1,
        "max_nodes": 1,
        "nproc_per_node": 1,
        "role": "benchmark_worker",
        "monitor_interval": 30,
        "rdzv_id": "647201d3-1b63-4512-a68e-b5e519f515bf",
        "rdzv_backend": "c10d",
        "rdzv_endpoint": "localhost:0",
        "rdzv_configs": {
            "rank": 0,
            "timeout": 900
        },
        "max_restarts": 0,
        "start_method": "spawn",
        "log_dir": null,
        "redirects": "0",
        "tee": "0",
        "metrics_cfg": {},
        "local_addr": null
    },
    "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,
        "latency": true,
        "memory": true,
        "energy": false,
        "forward_kwargs": {},
        "generate_kwargs": {},
        "call_kwargs": {}
    },
    "experiment_name": "api-launch",
    "task": null,
    "model": null,
    "device": null,
    "library": null,
    "environment": {
        "cpu": " Intel(R) Xeon(R) Gold 6448Y",
        "cpu_count": 16,
        "cpu_ram_mb": 237491.42528,
        "system": "Linux",
        "machine": "x86_64",
        "platform": "Linux-5.15.0-86-generic-x86_64-with-glibc2.35",
        "processor": "x86_64",
        "python_version": "3.10.12",
        "gpu": [
            "NVIDIA H100 80GB HBM3"
        ],
        "gpu_count": 1,
        "gpu_vram_mb": 85520809984,
        "optimum_benchmark_version": "0.2.0",
        "optimum_benchmark_commit": "9141f5b68a70cab5d9d5698b5bcefafd0c07270f",
        "transformers_version": "4.39.1",
        "transformers_commit": null,
        "accelerate_version": "0.25.0",
        "accelerate_commit": null,
        "diffusers_version": "0.15.0",
        "diffusers_commit": null,
        "optimum_version": "1.17.1",
        "optimum_commit": null,
        "timm_version": null,
        "timm_commit": null,
        "peft_version": "0.9.0",
        "peft_commit": null
    }
}