{ "current_gpu_type": "NVIDIA A100-PCIE-40GB", "current_gpu_total_memory": 40339.3125, "perplexity": Infinity, "token_generation_latency_sync": 43.16698951721192, "token_generation_latency_async": 43.36101561784744, "token_generation_throughput_sync": 0.02316584990485082, "token_generation_throughput_async": 0.023062190443445214, "token_generation_CO2_emissions": null, "token_generation_energy_consumption": null, "inference_latency_sync": 39.05454063415527, "inference_latency_async": 35.3114128112793, "inference_throughput_sync": 0.02560521731307849, "inference_throughput_async": 0.02831945596015848, "inference_CO2_emissions": null, "inference_energy_consumption": null }