|
{ |
|
"current_gpu_type": "Tesla T4", |
|
"current_gpu_total_memory": 15095.0625, |
|
"perplexity": 3.4586403369903564, |
|
"memory_inference_first": 810.0, |
|
"memory_inference": 808.0, |
|
"token_generation_latency_sync": 37.52931938171387, |
|
"token_generation_latency_async": 37.49031759798527, |
|
"token_generation_throughput_sync": 0.02664583361688273, |
|
"token_generation_throughput_async": 0.026673553708537804, |
|
"token_generation_CO2_emissions": 1.9795767676085165e-05, |
|
"token_generation_energy_consumption": 0.0018361529394885828, |
|
"inference_latency_sync": 122.5987979888916, |
|
"inference_latency_async": 48.247456550598145, |
|
"inference_throughput_sync": 0.008156686822415727, |
|
"inference_throughput_async": 0.020726481176293273, |
|
"inference_CO2_emissions": 1.9329542916591693e-05, |
|
"inference_energy_consumption": 6.80833538907916e-05 |
|
} |