{ "current_gpu_type": "NVIDIA A100-PCIE-40GB", "current_gpu_total_memory": 40339.3125, "perplexity": 6.83635950088501, "token_generation_latency_sync": 59.26941833496094, "token_generation_latency_async": 59.41547527909279, "token_generation_throughput_sync": 0.016872107540325487, "token_generation_throughput_async": 0.01683063200795234, "token_generation_CO2_emissions": null, "token_generation_energy_consumption": null, "inference_latency_sync": 183.77093200683595, "inference_latency_async": 105.75063228607178, "inference_throughput_sync": 0.005441556992064457, "inference_throughput_async": 0.009456208236134661, "inference_CO2_emissions": null, "inference_energy_consumption": null }