Radiant-Practice-270@alien.topB to LocalLLaMA@poweruser.forumEnglish · 10 months agoWhy is a single a100 so slow?plus-squaremessage-squaremessage-square8fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareWhy is a single a100 so slow?plus-squareRadiant-Practice-270@alien.topB to LocalLLaMA@poweruser.forumEnglish · 10 months agomessage-square8fedilink
minus-squareRadiant-Practice-270@alien.topOPBtoLocalLLaMA@poweruser.forum•How can I improve inference performance to a normal range?linkfedilinkEnglisharrow-up1·10 months agosry for late reply. i already test about that , it is better than codellama 13b model but , 30token/s … linkfedilink
Radiant-Practice-270@alien.topB to LocalLLaMA@poweruser.forumEnglish · 10 months agoHow can I improve inference performance to a normal range?plus-squaremessage-squaremessage-square2fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareHow can I improve inference performance to a normal range?plus-squareRadiant-Practice-270@alien.topB to LocalLLaMA@poweruser.forumEnglish · 10 months agomessage-square2fedilink
sry for late reply. i already test about that , it is better than codellama 13b model but , 30token/s …