ollama/docs/development.md

# 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 `go generate ./...`
- run `go build .`
add development doc 2023-06-27 17:46:46 +00:00			`# Development`

subprocess llama.cpp server (#401) * remove c code * pack llama.cpp * use request context for llama_cpp * let llama_cpp decide the number of threads to use * stop llama runner when app stops * remove sample count and duration metrics * use go generate to get libraries * tmp dir for running llm 2023-08-30 20:35:03 +00:00			`- Install cmake or (optionally, required tools for GPUs)`
			- run `go generate ./...`
			- run `go build .`

add publish script 2023-07-07 16:59:24 +00:00			`Install required tools:`
add development doc 2023-06-27 17:46:46 +00:00
first pass at linux gpu support (#454) * linux gpu support * handle multiple gpus * add cuda docker image (#488) --------- Co-authored-by: Michael Yang <mxyng@pm.me> 2023-09-12 15:04:35 +00:00			`- cmake version 3.24 or higher`
			`- go version 1.20 or higher`
			`- gcc version 11.4.0 or higher`

add development doc 2023-06-27 17:46:46 +00:00			```
subprocess llama.cpp server (#401) * remove c code * pack llama.cpp * use request context for llama_cpp * let llama_cpp decide the number of threads to use * stop llama runner when app stops * remove sample count and duration metrics * use go generate to get libraries * tmp dir for running llm 2023-08-30 20:35:03 +00:00			`brew install go cmake gcc`
add development doc 2023-06-27 17:46:46 +00:00			```

subprocess llama.cpp server (#401) * remove c code * pack llama.cpp * use request context for llama_cpp * let llama_cpp decide the number of threads to use * stop llama runner when app stops * remove sample count and duration metrics * use go generate to get libraries * tmp dir for running llm 2023-08-30 20:35:03 +00:00			`Get the required libraries:`
Note that CGO must be enabled in dev docs 2023-07-21 20:36:36 +00:00
			```
subprocess llama.cpp server (#401) * remove c code * pack llama.cpp * use request context for llama_cpp * let llama_cpp decide the number of threads to use * stop llama runner when app stops * remove sample count and duration metrics * use go generate to get libraries * tmp dir for running llm 2023-08-30 20:35:03 +00:00			`go generate ./...`
Note that CGO must be enabled in dev docs 2023-07-21 20:36:36 +00:00			```

Some simple modelfile examples Signed-off-by: Matt Williams <m@technovangelist.com> 2023-07-18 00:16:59 +00:00			`Then build ollama:`
add development doc 2023-06-27 17:46:46 +00:00
			```
Some simple modelfile examples Signed-off-by: Matt Williams <m@technovangelist.com> 2023-07-18 00:16:59 +00:00			`go build .`
add development doc 2023-06-27 17:46:46 +00:00			```

add publish script 2023-07-07 16:59:24 +00:00			Now you can run `ollama`:
add development doc 2023-06-27 17:46:46 +00:00
			```
add publish script 2023-07-07 16:59:24 +00:00			`./ollama`
add development doc 2023-06-27 17:46:46 +00:00			```
first pass at linux gpu support (#454) * linux gpu support * handle multiple gpus * add cuda docker image (#488) --------- Co-authored-by: Michael Yang <mxyng@pm.me> 2023-09-12 15:04:35 +00:00
			`## Building on Linux with GPU support`

			`- Install cmake and nvidia-cuda-toolkit`
embed libraries using cmake 2023-09-20 19:15:23 +00:00			- run `go generate ./...`
first pass at linux gpu support (#454) * linux gpu support * handle multiple gpus * add cuda docker image (#488) --------- Co-authored-by: Michael Yang <mxyng@pm.me> 2023-09-12 15:04:35 +00:00			- run `go build .`