data/mllm_text_generation/chat/A100-SXM4-40GB/llava-hf/llava-1.5-13b-hf/bs64+tp2+pp1.json

{
  "Model": "llava-hf/llava-1.5-13b-hf",
  "GPU": "NVIDIA A100-SXM4-40GB",
  "TP": 2,
  "PP": 1,
  "Energy/req (J)": 121.64585498503841,
  "Avg TPOT (s)": 0.0848595993021941,
  "Token tput (tok/s)": 607.490047799961,
  "Avg Output Tokens": 153.29,
  "Avg BS (reqs)": 63.492537313432834,
  "Max BS (reqs)": 64
}