data/mllm_text_generation/chat/A100-SXM4-40GB/llava-hf/llava-1.5-13b-hf/bs16+tp1+pp1.json

{
  "Model": "llava-hf/llava-1.5-13b-hf",
  "GPU": "NVIDIA A100-SXM4-40GB",
  "TP": 1,
  "PP": 1,
  "Energy/req (J)": 156.78159144940923,
  "Avg TPOT (s)": 0.05322914513543146,
  "Token tput (tok/s)": 290.2760002002473,
  "Avg Output Tokens": 152.316,
  "Avg BS (reqs)": 15.902582159624414,
  "Max BS (reqs)": 16
}