Jae-Won Chung
New leaderboard prototype
b10121d
raw
history blame contribute delete
323 Bytes
{
"Model": "codellama/CodeLlama-7b-hf",
"GPU": "NVIDIA A100-SXM4-40GB",
"TP": 1,
"PP": 1,
"Energy/req (J)": 19.26775474580916,
"Avg TPOT (s)": 0.08649359462573784,
"Token tput (tok/s)": 1306.71483863627,
"Avg Output Tokens": 99.06920731707316,
"Avg BS (reqs)": 126.98364657066146,
"Max BS (reqs)": 128
}