78 lines
1.5 KiB
Markdown
78 lines
1.5 KiB
Markdown
# Docker
|
|
|
|
There is a supplied docker image to make deploying a server as a container easier.
|
|
|
|
import Tabs from '@theme/Tabs';
|
|
import TabItem from '@theme/TabItem';
|
|
|
|
## CPU
|
|
|
|
<Tabs>
|
|
<TabItem value="shell" label="Shell" default>
|
|
|
|
```bash title="run.sh"
|
|
docker run -it \
|
|
-p 8080:8080 -v $HOME/.tabby:/data \
|
|
tabbyml/tabby serve --model TabbyML/SantaCoder-1B
|
|
```
|
|
|
|
</TabItem>
|
|
<TabItem value="compose" label="Docker Compose">
|
|
|
|
```yaml title="docker-compose.yml"
|
|
version: '3.5'
|
|
|
|
services:
|
|
tabby:
|
|
restart: always
|
|
image: tabbyml/tabby
|
|
command: serve --model TabbyML/SantaCoder-1B
|
|
volumes:
|
|
- "$HOME/.tabby:/data"
|
|
ports:
|
|
- 8080:8080
|
|
```
|
|
|
|
</TabItem>
|
|
</Tabs>
|
|
|
|
|
|
## CUDA (requires NVIDIA Container Toolkit)
|
|
|
|
<Tabs>
|
|
<TabItem value="shell" label="Shell" default>
|
|
|
|
```bash title="run.sh"
|
|
docker run -it \
|
|
--gpus all -p 8080:8080 -v $HOME/.tabby:/data \
|
|
tabbyml/tabby \
|
|
serve --model TabbyML/SantaCoder-1B --device cuda
|
|
```
|
|
|
|
</TabItem>
|
|
<TabItem value="compose" label="Docker Compose">
|
|
|
|
```yaml title="docker-compose.yml"
|
|
version: '3.5'
|
|
services:
|
|
tabby:
|
|
restart: always
|
|
image: tabbyml/tabby
|
|
command: serve --model TabbyML/SantaCoder-1B --device cuda
|
|
volumes:
|
|
- "$HOME/.tabby:/data"
|
|
ports:
|
|
- 8080:8080
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: 1
|
|
capabilities: [gpu]
|
|
```
|
|
|
|
</TabItem>
|
|
</Tabs>
|
|
|