I’m using a100 pcie 80g. Cuda11.8 toolkit 525.x

But when i inference codellama 13b with oobabooga(web ui)

It just make 5tokens/s

It is so slow.

Is there any config or something else for a100???

  • nuvalabB
    link
    fedilink
    English
    arrow-up
    1
    ·
    11 months ago

    That sounds like CPU speed. What you see from `watch nvidia-smi -d -n 0.1` while you’re running inference ?

  • a_beautiful_rhindB
    link
    fedilink
    English
    arrow-up
    1
    ·
    11 months ago

    Something is wrong with your environment. even P40s give more than that.

    Other option is you don’t get enough tokens to get proper t/s speed. What was the total inference time?

  • easyllaamaB
    link
    fedilink
    English
    arrow-up
    1
    ·
    11 months ago

    Try use GGUF, this format likes single GPU especially you have 80GB vram. I think you can run 70gb GGUF with all layers in GPU.