Jae-Won Chung
New leaderboard prototype
b10121d
raw
history blame contribute delete
325 Bytes
{
"Model": "codellama/CodeLlama-7b-hf",
"GPU": "NVIDIA A100-SXM4-40GB",
"TP": 2,
"PP": 1,
"Energy/req (J)": 23.51302786992996,
"Avg TPOT (s)": 0.1045348898830165,
"Token tput (tok/s)": 1532.6399423192706,
"Avg Output Tokens": 100.74176829268292,
"Avg BS (reqs)": 190.73771626297577,
"Max BS (reqs)": 192
}