You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs-content/docker.md
+8-8Lines changed: 8 additions & 8 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,6 +1,6 @@
1
1
# Docker — MaIN.NET InferPage
2
2
3
-
MaIN.NET ships a ready-to-run Docker image called **InferPage** (`ghcr.io/wisedev-code/main-inferpage`). It is a Blazor Server web app that wraps MaIN.NET and exposes a browser-based chat UI on **port 5555**. Zero code required — pull, run, chat.
3
+
MaIN.NET ships a ready-to-run Docker image called **InferPage** (`ghcr.io/mobitouchos/main-inferpage`). It is a Blazor Server web app that wraps MaIN.NET and exposes a browser-based chat UI on **port 5555**. Zero code required — pull, run, chat.
4
4
5
5
InferPage is genuinely multiplatform. The same repo produces four image tags targeting different hardware:
6
6
@@ -40,7 +40,7 @@ InferPage is genuinely multiplatform. The same repo produces four image tags tar
40
40
docker run -d \
41
41
-p 5555:5555 \
42
42
-v ~/models:/app/Models \
43
-
ghcr.io/wisedev-code/main-inferpage:cpu
43
+
ghcr.io/mobitouchos/main-inferpage:cpu
44
44
```
45
45
46
46
### Windows / Linux with NVIDIA GPU
@@ -52,15 +52,15 @@ docker run -d \
52
52
--gpus all \
53
53
-p 5555:5555 \
54
54
-v ~/models:/app/Models \
55
-
ghcr.io/wisedev-code/main-inferpage:cuda
55
+
ghcr.io/mobitouchos/main-inferpage:cuda
56
56
```
57
57
58
58
### External Ollama (Ollama already running on the host)
59
59
60
60
```bash
61
61
docker run -d \
62
62
-p 5555:5555 \
63
-
ghcr.io/wisedev-code/main-inferpage:ollama
63
+
ghcr.io/mobitouchos/main-inferpage:ollama
64
64
```
65
65
66
66
The `:ollama` image defaults `MaIN__OllamaBaseUrl` to `http://host.docker.internal:11434`. Override this to point at a remote Ollama.
@@ -71,7 +71,7 @@ The `:ollama` image defaults `MaIN__OllamaBaseUrl` to `http://host.docker.intern
Copy file name to clipboardExpand all lines: frontend/public/docs/docker.md
+6-6Lines changed: 6 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -24,7 +24,7 @@ It is **genuinely multiplatform**:
24
24
docker run -d \
25
25
-p 5555:5555 \
26
26
-v ~/models:/app/Models \
27
-
ghcr.io/wisedev-code/main-inferpage:cpu
27
+
ghcr.io/mobitouchos/main-inferpage:cpu
28
28
```
29
29
30
30
Open `http://localhost:5555` — done.
@@ -36,7 +36,7 @@ docker run -d \
36
36
--gpus all \
37
37
-p 5555:5555 \
38
38
-v ~/models:/app/Models \
39
-
ghcr.io/wisedev-code/main-inferpage:cuda
39
+
ghcr.io/mobitouchos/main-inferpage:cuda
40
40
```
41
41
42
42
The `:cuda` image is based on `nvidia/cuda:12.9.1-runtime-ubuntu24.04` and automatically enables all visible GPUs. Make sure the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html) is installed.
@@ -49,7 +49,7 @@ If you already have Ollama running locally, skip the model volume entirely:
0 commit comments