Skip to content

declare required ACP version for knative operator #129

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
fyuan1316 merged 3 commits into from
Mar 9, 2026
Merged

declare required ACP version for knative operator #129

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
979f6bb
declare required ACP version for knative operator
fyuan1316 Mar 6, 2026
f15ea63
change version to 1.18.1
fyuan1316 Mar 6, 2026
21aa499
use new name Alauda Build os KServe
fyuan1316 Mar 9, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 8 additions & 1 deletion docs/en/installation/ai-cluster.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -291,6 +291,9 @@ Once **Knative Operator** is installed, you need to create the `KnativeServing`
name: knative-serving
namespace: knative-serving
spec:
# For ACP 4.0, use version 1.18.1
# For ACP 4.1 and above, use version 1.19.6
version: "1.18.1" # [!code callout]
config:
deployment:
registries-skipping-tag-resolving: kind.local,ko.local,dev.local,private-registry # [!code callout]
Expand Down Expand Up @@ -318,7 +321,11 @@ Once **Knative Operator** is installed, you need to create the `KnativeServing`

<Callouts>

1. `private-registry` is a placeholder for your private registry address. You can find this in the **Administrator** view, then click **Clusters**, select `your cluster`, and check the **Private Registry** value in the **Basic Info** section.
1. For ACP 4.0, keep the version as "1.18.1". For ACP 4.1 and above, change the version to "1.19.6".

2. `private-registry` is a placeholder for your private registry address. You can find this in the **Administrator** view, then click **Clusters**, select `your cluster`, and check the **Private Registry** value in the **Basic Info** section.



</Callouts>

Expand Down
25 changes: 12 additions & 13 deletions docs/en/installation/ai-generative.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,15 +2,14 @@
weight: 35
---

# Install Alauda AI Generative
# Install Alauda Build of KServe

**Alauda AI Generative** is a cloud-native component built on **KServe** for serving generative AI models. As an extension of the Alauda AI ecosystem, it specifically optimizes for **Large Language Models (LLMs)**, offering essential features such as inference orchestration, streaming responses, and resource-based auto-scaling for generative workloads.
**Alauda Build of KServe** is a cloud-native component built on **KServe** for serving generative AI models. As an extension of the Alauda AI ecosystem, it specifically optimizes for **Large Language Models (LLMs)**, offering essential features such as inference orchestration, streaming responses, and resource-based auto-scaling for generative workloads.

---

## Prerequisites

Before installing **Alauda AI Generative**, you need to ensure the following dependencies are installed:
Before installing **Alauda Build of KServe**, you need to ensure the following dependencies are installed:

### Required Dependencies

Expand All @@ -28,20 +27,20 @@ Before installing **Alauda AI Generative**, you need to ensure the following dep

| Dependency | Type | Description |
|------------|------|-------------|
| GIE | Built-in | Integrated GIE (gateway-api-inference-extension) for enhanced AI capabilities. Can be enabled through the Alauda AI Generative UI. |
| GIE | Built-in | Integrated GIE (gateway-api-inference-extension) for enhanced AI capabilities. Can be enabled through the Alauda Build of KServe UI. |
| Alauda AI | Operator | Required only if you need to use KServe Predictive AI functionality. Can be disabled if you only need LLM Generative AI functionality. |

### Installation Notes

1. **Required Dependencies**: All three required dependencies must be installed before installing Alauda AI Generative.
2. **GIE Integration**: If you want to use GIE, you can enable it during the installation process by selecting the "Integrated GIE" option in the Alauda AI Generative UI.
1. **Required Dependencies**: All three required dependencies must be installed before installing Alauda Build of KServe.
2. **GIE Integration**: If you want to use GIE, you can enable it during the installation process by selecting the "Integrated GIE" option in the Alauda Build of KServe UI.
3. **Alauda AI Integration**: If you don't need KServe Predictive AI functionality and only want to use LLM Generative AI, you can disable the "Integrated With Alauda AI" option during installation.

## Downloading Cluster Plugin

:::info

`Alauda AI Generative` cluster plugin can be retrieved from Customer Portal.
`Alauda Build of KServe` cluster plugin can be retrieved from Customer Portal.

Please contact Consumer Support for more information.

Expand All @@ -51,9 +50,9 @@ Please contact Consumer Support for more information.

For more information on uploading the cluster plugin, please refer to <ExternalSiteLink name="acp" href="ui/cli_tools/index.html#uploading-cluster-plugins" children="Uploading Cluster Plugins" />

## Installing Alauda AI Generative
## Installing Alauda Build of KServe

1. Go to the `Administrator` -> `Marketplace` -> `Cluster Plugin` page, switch to the target cluster, and then deploy the `Alauda AI Generative` Cluster plugin.
1. Go to the `Administrator` -> `Marketplace` -> `Cluster Plugin` page, switch to the target cluster, and then deploy the `Alauda Build of KServe` Cluster plugin.

2. In the deployment form, configure the following parameters as needed:

Expand Down Expand Up @@ -99,7 +98,7 @@ For more information on uploading the cluster plugin, please refer to <ExternalS

4. Verify result. You can see the status of "Installed" in the UI.

## Upgrading Alauda AI Generative
## Upgrading Alauda Build of KServe

1. Upload the new version for package of **Alauda AI Generative** plugin to ACP.
2. Go to the `Administrator` -> `Clusters` -> `Target Cluster` -> `Functional Components` page, then click the `Upgrade` button, and you will see the `Alauda AI Generative` can be upgraded.
1. Upload the new version for package of **Alauda Build of KServe** plugin to ACP.
2. Go to the `Administrator` -> `Clusters` -> `Target Cluster` -> `Functional Components` page, then click the `Upgrade` button, and you will see the `Alauda Build of KServe` can be upgraded.
Comment on lines +103 to +104
Copy link
Copy Markdown

@coderabbitai coderabbitai bot Mar 6, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor

Tighten the upgrade wording.

Upload the new version for package of ... and you will see the ... can be upgraded read awkwardly in user-facing instructions. Please rewrite these two steps into direct, grammatical actions before publishing.

🤖 Prompt for AI Agents 
Verify each finding against the current code and only fix it if needed.

In `@docs/en/installation/ai-generative.mdx` around lines 103 - 104, Rewrite the
two steps to use direct, grammatical imperative sentences: change "Upload the
new version for package of **Alauda Build of KServe** plugin to ACP." to
something like "Upload the new version of the Alauda Build of KServe plugin to
ACP." and change "you will see the `Alauda Build of KServe` can be upgraded." to
something like "The Alauda Build of KServe will be listed with an available
Upgrade option; click Upgrade." Replace the original lines (the sentence
containing "Upload the new version for package of" and the sentence containing
"you will see the `Alauda Build of KServe` can be upgraded") with these direct,
grammatical imperative forms.

6 changes: 3 additions & 3 deletions docs/en/overview/architecture.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,9 +46,9 @@ The diagram below illustrates the architecture of the Alauda AI platform.

| Component | Description | Type | License |
| --- | --- | --- | --- |
| Kserve (Alauda AI Model Serving/Alauda Generative AI) | Kubernetes-native model serving framework | Open source | Apache Version 2.0 |
| vLLM (Alauda AI Model Serving/Alauda Generative AI) | High-performance model inference engine for large language models | Open source | Apache Version 2.0 |
| llm-d (Alauda Generative AI) | Distributed inference engine for large language models | Open source | Apache Version 2.0 |
| Kserve (Alauda AI/Alauda Build of KServe) | Kubernetes-native model serving framework | Open source | Apache Version 2.0 |
| vLLM (Alauda AI/Alauda Build of KServe) | High-performance model inference engine for large language models | Open source | Apache Version 2.0 |
Copy link
Copy Markdown

@coderabbitai coderabbitai bot Mar 9, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor

🧩 Analysis chain

🏁 Script executed:

# First, let's check the architecture.mdx file around line 50
cat -n docs/en/overview/architecture.mdx | sed -n '45,55p'

Repository: alauda/aml-docs

Length of output: 1199

🏁 Script executed:

# Check the inference_service.mdx file around the mentioned lines
cat -n docs/en/model_inference/inference_service/functions/inference_service.mdx | sed -n '38,52p'

Repository: alauda/aml-docs

Length of output: 903

🏁 Script executed:

# Let's also search for other references to vLLM in the documentation
rg -n "vLLM" docs/ --type markdown

Repository: alauda/aml-docs

Length of output: 41

Clarify the vLLM product label to reflect it as a separate inference runtime.

The label (Alauda AI/Alauda Build of KServe) is inconsistent and misleading. It incorrectly associates vLLM with KServe when vLLM is a distinct inference framework, as documented in docs/en/model_inference/inference_service/functions/inference_service.mdx:43–47, which lists vLLM as a separate mainstream inference framework alongside MLServer. Additionally, the label breaks the pattern used elsewhere in the table (e.g., KServe and llm-d both use "Alauda Build of X"). Update the label to clarify vLLM as its own runtime—either (Alauda Build of vLLM), (Alauda AI vLLM), or a single consistent branding choice.

🤖 Prompt for AI Agents 
Verify each finding against the current code and only fix it if needed.

In `@docs/en/overview/architecture.mdx` at line 50, Update the vLLM table row
label so it clearly identifies vLLM as its own inference runtime instead of
associating it with KServe: replace the substring "(Alauda AI/Alauda Build of
KServe)" in the vLLM row (the table line containing "vLLM (Alauda AI/Alauda
Build of KServe)") with a consistent branding choice such as "(Alauda Build of
vLLM)" or "(Alauda AI vLLM)"; ensure the change mirrors the pattern used for
other entries like "KServe" and "llm-d" so the table consistently shows separate
runtimes.

| llm-d (Alauda Build of KServe) | Distributed inference engine for large language models | Open source | Apache Version 2.0 |
| Model as a Service (Alauda build of Envoy AI Gateway) | API gateway for serving AI models as a service | Open source | Apache Version 2.0 |
| Fine-tuning | Tools integrated with the workbench for fine-tuning large language models, e.g. transformers, accelerate, llama-factory etc. | Open source | - |
| Training (Alauda support for Kubeflow Trainer v2) | Kubernetes-native training job management | Open source | Apache Version 2.0 |
Expand Down