JotaOdiceu
f568e43362
Covers building, installing, running models with llama-server, and complete uninstallation of llama.cpp.
78 lines
1.2 KiB
Markdown
78 lines
1.2 KiB
Markdown
# Install llama.cpp
|
|
|
|
This recipe builds and installs llama.cpp from source on Debian/Ubuntu, including build dependencies and the `llama-server` binary.
|
|
|
|
## Install Build Dependencies
|
|
|
|
```bash
|
|
sudo apt update
|
|
sudo apt install -y build-essential cmake git libcurl4-openssl-dev
|
|
```
|
|
|
|
## Clone Repository
|
|
|
|
```bash
|
|
git clone https://github.com/ggml-org/llama.cpp
|
|
cd llama.cpp
|
|
```
|
|
|
|
## Build Project
|
|
|
|
```bash
|
|
cmake -B build
|
|
cmake --build build --config Release -j $(nproc)
|
|
```
|
|
|
|
## Install Binaries
|
|
|
|
```bash
|
|
sudo cmake --install build
|
|
sudo ldconfig
|
|
```
|
|
|
|
## Verify Installation
|
|
|
|
```bash
|
|
llama-server --version
|
|
```
|
|
|
|
Expected output:
|
|
|
|
```text
|
|
version: xxxx (xxxxxxxx)
|
|
```
|
|
|
|
## Verify Binary Location
|
|
|
|
```bash
|
|
which llama-server
|
|
```
|
|
|
|
Expected output:
|
|
|
|
```text
|
|
/usr/local/bin/llama-server
|
|
```
|
|
|
|
## Troubleshooting
|
|
|
|
### Command not found
|
|
|
|
Verify that the binary was installed.
|
|
|
|
```bash
|
|
ls /usr/local/bin/llama-server
|
|
```
|
|
|
|
If it is missing, repeat the build and install steps.
|
|
|
|
### Build fails with missing dependency
|
|
|
|
Verify the build dependencies are installed.
|
|
|
|
```bash
|
|
dpkg -l | grep -E "build-essential|cmake|libcurl4-openssl-dev"
|
|
```
|
|
|
|
If any are missing, repeat the dependency installation step.
|