Skip to content

Commit adfa7aa

Browse files
authored
docs: site update fixing old image text / How To update updating GPU and CPU docker pages (#1399)
* Update _index.en.md Signed-off-by: lunamidori5 <[email protected]> * Update easy-setup-docker-cpu.md Signed-off-by: lunamidori5 <[email protected]> * Update easy-setup-docker-gpu.md Signed-off-by: lunamidori5 <[email protected]> --------- Signed-off-by: lunamidori5 <[email protected]>
1 parent 8b6e601 commit adfa7aa

File tree

3 files changed

+63
-18
lines changed

3 files changed

+63
-18
lines changed

docs/content/getting_started/_index.en.md

Lines changed: 39 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -183,20 +183,48 @@ You can control LocalAI with command line arguments, to specify a binding addres
183183

184184
LocalAI has a set of images to support CUDA, ffmpeg and 'vanilla' (CPU-only). The image list is on [quay](https://quay.io/repository/go-skynet/local-ai?tab=tags):
185185

186-
- Vanilla images tags: `master`, `v1.40.0`, `latest`, ...
187-
- FFmpeg images tags: `master-ffmpeg`, `v1.40.0-ffmpeg`, ...
188-
- CUDA `11` tags: `master-cublas-cuda11`, `v1.40.0-cublas-cuda11`, ...
189-
- CUDA `12` tags: `master-cublas-cuda12`, `v1.40.0-cublas-cuda12`, ...
190-
- CUDA `11` + FFmpeg tags: `master-cublas-cuda11-ffmpeg`, `v1.40.0-cublas-cuda11-ffmpeg`, ...
191-
- CUDA `12` + FFmpeg tags: `master-cublas-cuda12-ffmpeg`, `v1.40.0-cublas-cuda12-ffmpeg`, ...
192-
- Core images (smaller images without python dependencies): `master-core`, `v1.40.0-core`, ...
186+
{{< tabs >}}
187+
{{% tab name="Vanilla / CPU Images" %}}
188+
- `master`
189+
- `latest`
190+
- `v2.0.0`
191+
- `v2.0.0-ffmpeg`
192+
- `v2.0.0-ffmpeg-core`
193+
194+
Core Images - Smaller images without predownload python dependencies
195+
{{% /tab %}}
196+
197+
{{% tab name="GPU Images CUDA 11" %}}
198+
- `master-cublas-cuda11`
199+
- `master-cublas-cuda11-core`
200+
- `v2.0.0-cublas-cuda11`
201+
- `v2.0.0-cublas-cuda11-core`
202+
- `v2.0.0-cublas-cuda11-ffmpeg`
203+
- `v2.0.0-cublas-cuda11-ffmpeg-core`
204+
205+
Core Images - Smaller images without predownload python dependencies
206+
{{% /tab %}}
207+
208+
{{% tab name="GPU Images CUDA 12" %}}
209+
- `master-cublas-cuda12`
210+
- `master-cublas-cuda12-core`
211+
- `v2.0.0-cublas-cuda12`
212+
- `v2.0.0-cublas-cuda12-core`
213+
- `v2.0.0-cublas-cuda12-ffmpeg`
214+
- `v2.0.0-cublas-cuda12-ffmpeg-core`
215+
216+
Core Images - Smaller images without predownload python dependencies
217+
218+
{{% /tab %}}
219+
220+
{{< /tabs >}}
193221

194222
Example:
195223

196224
- Standard (GPT + `stablediffusion`): `quay.io/go-skynet/local-ai:latest`
197-
- FFmpeg: `quay.io/go-skynet/local-ai:v1.40.0-ffmpeg`
198-
- CUDA 11+FFmpeg: `quay.io/go-skynet/local-ai:v1.40.0-cublas-cuda11-ffmpeg`
199-
- CUDA 12+FFmpeg: `quay.io/go-skynet/local-ai:v1.40.0-cublas-cuda12-ffmpeg`
225+
- FFmpeg: `quay.io/go-skynet/local-ai:v2.0.0-ffmpeg`
226+
- CUDA 11+FFmpeg: `quay.io/go-skynet/local-ai:v2.0.0-cublas-cuda11-ffmpeg`
227+
- CUDA 12+FFmpeg: `quay.io/go-skynet/local-ai:v2.0.0-cublas-cuda12-ffmpeg`
200228

201229
{{% notice note %}}
202230
Note: the binary inside the image is pre-compiled, and might not suite all CPUs.
@@ -237,7 +265,7 @@ Deploy a single LocalAI pod with 6GB of persistent storage serving up a `ggml-gp
237265
replicaCount: 1
238266
239267
deployment:
240-
image: quay.io/go-skynet/local-ai:latest ##(This is for CPU only, to use GPU change it to a image that supports GPU IE "v1.40.0-cublas-cuda12")
268+
image: quay.io/go-skynet/local-ai:latest ##(This is for CPU only, to use GPU change it to a image that supports GPU IE "v2.0.0-cublas-cuda12-core")
241269
env:
242270
threads: 4
243271
context_size: 512

docs/content/howtos/easy-setup-docker-cpu.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -85,7 +85,7 @@ version: '3.6'
8585
8686
services:
8787
api:
88-
image: quay.io/go-skynet/local-ai:v1.40.0
88+
image: quay.io/go-skynet/local-ai:v2.0.0
8989
tty: true # enable colorized logs
9090
restart: always # should this be on-failure ?
9191
ports:

docs/content/howtos/easy-setup-docker-gpu.md

Lines changed: 23 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -81,12 +81,29 @@ It will use a container from [quay.io](https://quay.io/repository/go-skynet/loca
8181
Also note this `docker-compose` file is for `CUDA` only.
8282

8383
Please change the image to what you need.
84-
```
85-
Cuda 11 - v1.40.0-cublas-cuda11
86-
Cuda 12 - v1.40.0-cublas-cuda12
87-
Cuda 11 with TTS - v1.40.0-cublas-cuda11-ffmpeg
88-
Cuda 12 with TTS - v1.40.0-cublas-cuda12-ffmpeg
89-
```
84+
{{< tabs >}}
85+
{{% tab name="GPU Images CUDA 11" %}}
86+
- `master-cublas-cuda11`
87+
- `master-cublas-cuda11-core`
88+
- `v2.0.0-cublas-cuda11`
89+
- `v2.0.0-cublas-cuda11-core`
90+
- `v2.0.0-cublas-cuda11-ffmpeg`
91+
- `v2.0.0-cublas-cuda11-ffmpeg-core`
92+
93+
Core Images - Smaller images without predownload python dependencies
94+
{{% /tab %}}
95+
96+
{{% tab name="GPU Images CUDA 12" %}}
97+
- `master-cublas-cuda12`
98+
- `master-cublas-cuda12-core`
99+
- `v2.0.0-cublas-cuda12`
100+
- `v2.0.0-cublas-cuda12-core`
101+
- `v2.0.0-cublas-cuda12-ffmpeg`
102+
- `v2.0.0-cublas-cuda12-ffmpeg-core`
103+
104+
Core Images - Smaller images without predownload python dependencies
105+
{{% /tab %}}
106+
{{< /tabs >}}
90107

91108
```docker
92109
version: '3.6'

0 commit comments

Comments
 (0)