support for packaging in multiple cuda runners (#509)

* enable packaging multiple cuda versions
* use nvcc cuda version if available

---------

Co-authored-by: Michael Yang <mxyng@pm.me>
This commit is contained in:
Bruce MacDonald
2023-09-14 15:08:13 -04:00
committed by GitHub
parent 83ffb154bc
commit 2540c9181c
5 changed files with 96 additions and 38 deletions

View File

@@ -35,5 +35,5 @@ Now you can run `ollama`:
## Building on Linux with GPU support
- Install cmake and nvidia-cuda-toolkit
- run `go generate ./...`
- run `CUDA_VERSION=$(nvcc --version | sed -n 's/^.*release \([0-9]\+\)\.\([0-9]\+\).*$/\1/p') go generate ./...`
- run `go build .`