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
This should be the URL you generated and hosted in the previous step.
65
+
66
+
You may also use any internally hosted ISO that is reachable by iDRAC.
67
+
68
+
> Note: If ISO_URL is not provided, the script will automatically use the default Ubuntu 22.04 Live Server ISO. it will Launch the standard installer and Prompt for manual user input during OS installation.
69
+
30
70
**Mount ISO**
31
71
```bash
32
72
chmod +x mount-iso.sh
@@ -40,15 +80,9 @@ chmod +x mount-iso.sh
40
80
41
81
Terraform uses the **Dell Redfish provider** to configure a **one-time boot from Virtual Media (CD)** and **force a reboot**.
42
82
43
-
Key Notes
44
-
- ISO must already be mounted using mount-iso.sh
45
-
- Boot override is set to Once
46
-
- Power reset is forced using redfish_power
47
-
- Boot mode (UEFI/Legacy) is not configurable on 17G servers
48
-
49
83
**Terraform Installation (Client Machine)**
50
84
51
-
> **Note:**Terraform is executed from a client machine (such as your laptop or a jump host), not from the target server or iDRAC.
85
+
Terraform is executed from a client machine (such as your laptop or a jump host), not from the target server or iDRAC.
52
86
53
87
Install Terraform on the machine where you will run the Terraform commands.
54
88
@@ -99,18 +133,6 @@ Once OS is installed, Download the deploy-enterprise-inference.sh script to your
99
133
100
134
This script performs **all post-OS configuration** and deploys the **Enterprise Inference stack** on a **single node**.
| -m | Choose model ID from [Pre-Integrated Models List](#pre-integrated-models-list) , based on your deployment type (gaudi or cpu) |
138
-
| -b | Repo branch (default: release-1.4.0) |
139
-
| -a | cluster -url |
140
-
| -r | Resume from last checkpoint |
141
-
| -d | keycloak or genai, by default set to keycloak |
142
-
| -o | off or on, by default observability set to off |
152
+
### Options & Defaults
153
+
154
+
| Option | Required | Default | Description |
155
+
|--------|----------|----------|-------------|
156
+
|`-u, --username`| Yes (deploy & uninstall) | (none) | Enterprise Inference owner username. Must match the invoking (sudo) user. |
157
+
|`-t, --token`| Yes (deploy only) | (none) | Hugging Face access token used to validate and download selected models. |
158
+
|`-p, --password`| No |`Linux123!`| User sudo password used for Ansible become operations. |
159
+
|`-g, --gpu-type`| No |`gaudi3`| Deployment target type: `gaudi3` or `cpu`. |
160
+
|`-m, --models`| No |`""` (interactive mode) | Choose model ID from [Pre-Integrated Models List](#pre-integrated-models-list) , based on your deployment type (gaudi or cpu) . If not provided, deployment runs interactively. |
161
+
|`-b, --branch`| No |`release-1.4.0`| Git branch of the Enterprise-Inference repository to clone. |
162
+
|`-f, --firmware-version`| No |`1.22.1`| Gaudi3 firmware version (applies only when `-g gaudi3`). |
163
+
|`-d, --deployment-mode`| No |`keycloak`| Deployment mode: `keycloak` (Keycloak + APISIX) or `genai` (GenAI Gateway). |
164
+
|`-o, --observability`| No |`off`| Enable observability components: `on` or `off`. |
165
+
|`-r, --resume`| No | Auto-detected | Resume deployment from last checkpoint if state file exists. |
166
+
|`-s, --state-file`| No |`/tmp/ei-deploy.state`| Custom path for deployment state tracking file. |
167
+
|`-a, --api-fqdn`| No |`api.example.com`| API Fully Qualified Domain Name used for `/etc/hosts` and TLS certificate generation. |
168
+
|`uninstall`| Yes (for uninstall action) | (none) | Removes deployed Enterprise Inference stack and cleans up state. |
169
+
143
170
144
171
**Resume After Failure**
145
172
@@ -269,6 +296,7 @@ if EI is deployed with apisix, follow [Testing EI model with apisix](../EI/singl
269
296
if EI is deployed with genai, follow [Testing EI model with genai](../EI/single-node/user-guide-genai.md#5-test-the-inference) for generating api-key and testing the inference
270
297
271
298
---
299
+
272
300
## Additional Information
273
301
274
302
### Pre-Integrated Models List
@@ -321,5 +349,3 @@ Refer to the [Model Deployment guide](./model-deployment.md) and run the interac
321
349
This repository provides a clean, deterministic, enterprise-grade deployment pipeline for:
0 commit comments