data/mllm_text_generation/chat/A100-SXM4-40GB/llava-hf/llava-1.5-13b-hf/bs32+tp2+pp1.json

{
  "Model": "llava-hf/llava-1.5-13b-hf",
  "GPU": "NVIDIA A100-SXM4-40GB",
  "TP": 2,
  "PP": 1,
  "Energy/req (J)": 143.9940187268745,
  "Avg TPOT (s)": 0.059400404627334875,
  "Token tput (tok/s)": 489.4861080312391,
  "Avg Output Tokens": 154.206,
  "Avg BS (reqs)": 31.803146725210393,
  "Max BS (reqs)": 32
}