data/mllm_text_generation/chat/A100-SXM4-40GB/llava-hf/llava-1.5-13b-hf/bs16+tp2+pp1.json

{
  "Model": "llava-hf/llava-1.5-13b-hf",
  "GPU": "NVIDIA A100-SXM4-40GB",
  "TP": 2,
  "PP": 1,
  "Energy/req (J)": 187.88988833751483,
  "Avg TPOT (s)": 0.045710293178024386,
  "Token tput (tok/s)": 336.4674382502306,
  "Avg Output Tokens": 155.65,
  "Avg BS (reqs)": 15.904296125815113,
  "Max BS (reqs)": 16
}