2540c9181c
* enable packaging multiple cuda versions * use nvcc cuda version if available --------- Co-authored-by: Michael Yang <mxyng@pm.me>
39 lines
622 B
Markdown
39 lines
622 B
Markdown
# Development
|
|
|
|
- Install cmake or (optionally, required tools for GPUs)
|
|
- run `go generate ./...`
|
|
- run `go build .`
|
|
|
|
Install required tools:
|
|
|
|
- cmake version 3.24 or higher
|
|
- go version 1.20 or higher
|
|
- gcc version 11.4.0 or higher
|
|
|
|
```
|
|
brew install go cmake gcc
|
|
```
|
|
|
|
Get the required libraries:
|
|
|
|
```
|
|
go generate ./...
|
|
```
|
|
|
|
Then build ollama:
|
|
|
|
```
|
|
go build .
|
|
```
|
|
|
|
Now you can run `ollama`:
|
|
|
|
```
|
|
./ollama
|
|
```
|
|
|
|
## Building on Linux with GPU support
|
|
|
|
- Install cmake and nvidia-cuda-toolkit
|
|
- run `CUDA_VERSION=$(nvcc --version | sed -n 's/^.*release \([0-9]\+\)\.\([0-9]\+\).*$/\1/p') go generate ./...`
|
|
- run `go build .`
|