a bug to use 16 * A10(16 * 23g) to inference llama2-70b

[babytdream]

I have 16 gpus in one machine.

Hello!when I use 16 * A10(16 * 23g) to inference llama2-70b, it appears error:

I ask many people to solve this problem,but failed.
I know 8 gpu can work it! But I need to increase the prompt of llama2, the 8 GPU is not enough!
Do you have some ideas, thanks!