ggllm.cpp icon indicating copy to clipboard operation
ggllm.cpp copied to clipboard

Log the version of cuda that is being used

Open WilliamTambellini opened this issue 2 years ago • 0 comments

Prerequisites

  • [X ] I am running the latest code. Development is very rapid so there are no tagged versions as of now.
  • [X ] I carefully followed the README.md.
  • [X ] I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
  • [X ] I reviewed the Discussions, and have a new bug or useful enhancement to share.

Your exact command line to replicate the issue

./falcon_main ....

Environment and Context

  • Physical (or virtual) hardware you are using, e.g. for Linux: intel cpu
  • Operating System, e.g. for Linux: CentOS

Steps to Reproduce

  1. ./falcon_main ...
  2. see in the log: "falcon_model_load_internal: using CUDA for GPU acceleration"
  3. desired: "falcon_model_load_internal: using CUDA 11.8 for GPU acceleration"

WilliamTambellini avatar Aug 01 '23 19:08 WilliamTambellini