data/llm_text_generation/code/A100-SXM4-40GB/codellama/CodeLlama-34b-hf/bs768+tp4+pp1.json

{
  "Model": "codellama/CodeLlama-34b-hf",
  "GPU": "NVIDIA A100-SXM4-40GB",
  "TP": 4,
  "PP": 1,
  "Energy/req (J)": 60.041989532010376,
  "Avg TPOT (s)": 0.2758757651143581,
  "Token tput (tok/s)": 1252.8344234896067,
  "Avg Output Tokens": 85.52865853658537,
  "Avg BS (reqs)": 740.1575757575757,
  "Max BS (reqs)": 768
}