data/llm_text_generation/code/A100-SXM4-40GB/codellama/CodeLlama-34b-hf/bs128+tp4+pp1.json

{
  "Model": "codellama/CodeLlama-34b-hf",
  "GPU": "NVIDIA A100-SXM4-40GB",
  "TP": 4,
  "PP": 1,
  "Energy/req (J)": 73.18930929564482,
  "Avg TPOT (s)": 0.12974827011374993,
  "Token tput (tok/s)": 877.4412103235645,
  "Avg Output Tokens": 86.91829268292683,
  "Avg BS (reqs)": 127.07475127722506,
  "Max BS (reqs)": 128
}