update

versioned_docs/version-v1.3.0/installation/offline-installation.md

@@ -2,58 +2,4 @@
 title: Offline Installation
 ---
 
-This document describes how you can use the `hack/remote-up-karmada.sh` script to install Karmada on
-your clusters based on the codebase.
-
-## Select a way to expose karmada-apiserver
-
-The `hack/remote-up-karmada.sh` will install `karmada-apiserver` and provide two ways to expose the server:
-
-### 1. expose by `HostNetwork` type
-
-By default, the `hack/remote-up-karmada.sh` will expose `karmada-apiserver` by `HostNetwork`.
-
-No extra operations needed with this type.
-
-### 2. expose by service with `LoadBalancer` type
-
-If you don't want to use the `HostNetwork`, you can ask `hack/remote-up-karmada.sh` to expose `karmada-apiserver`
-by a service with `LoadBalancer` type that *requires your cluster have deployed the `Load Balancer`*.
-All you need to do is set an environment:
-```bash
-export LOAD_BALANCER=true
-```
-
-## Install
-From the `root` directory the `karmada` repo, install Karmada by command:
-```bash
-hack/remote-up-karmada.sh <kubeconfig> <context_name>
-```
-- `kubeconfig` is your cluster's kubeconfig that you want to install to
-- `context_name` is the name of context in 'kubeconfig'
-
-For example:
-```bash
-hack/remote-up-karmada.sh $HOME/.kube/config mycluster
-```
-
-If everything goes well, at the end of the script output, you will see similar messages as follows:
-```
-------------------------------------------------------------------------------------------------------
-█████   ████   █████████   ███████████   ██████   ██████   █████████   ██████████     █████████
-░░███   ███░   ███░░░░░███ ░░███░░░░░███ ░░██████ ██████   ███░░░░░███ ░░███░░░░███   ███░░░░░███
-░███  ███    ░███    ░███  ░███    ░███  ░███░█████░███  ░███    ░███  ░███   ░░███ ░███    ░███
-░███████     ░███████████  ░██████████   ░███░░███ ░███  ░███████████  ░███    ░███ ░███████████
-░███░░███    ░███░░░░░███  ░███░░░░░███  ░███ ░░░  ░███  ░███░░░░░███  ░███    ░███ ░███░░░░░███
-░███ ░░███   ░███    ░███  ░███    ░███  ░███      ░███  ░███    ░███  ░███    ███  ░███    ░███
-█████ ░░████ █████   █████ █████   █████ █████     █████ █████   █████ ██████████   █████   █████
-░░░░░   ░░░░ ░░░░░   ░░░░░ ░░░░░   ░░░░░ ░░░░░     ░░░░░ ░░░░░   ░░░░░ ░░░░░░░░░░   ░░░░░   ░░░░░
-------------------------------------------------------------------------------------------------------
-Karmada is installed successfully.
-
-Kubeconfig for karmada in file: /root/.kube/karmada.config, so you can run:
-  export KUBECONFIG="/root/.kube/karmada.config"
-Or use kubectl with --kubeconfig=/root/.kube/karmada.config
-Please use 'kubectl config use-context karmada-apiserver' to switch the cluster of karmada control plane
-And use 'kubectl config use-context your-host' for debugging karmada installation
-```
+TODO

versioned_docs/version-v1.3.0/installation/online-installation.md

@@ -2,52 +2,40 @@
 title: Online Installation from Helm (Recommended)
 ---
 
-You can install `kubectl-karmada` plug-in in any of the following ways:
+The best practice to deploy HAMi is using helm. 
 
-- Download from the release.
-- Install using Krew.
-- Build from source code.
+## Add HAMi repo
 
-## Prerequisites
+You can add HAMi chart repository using the following command:
 
-### kubectl
-`kubectl` is the Kubernetes command line tool lets you control Kubernetes clusters.
-For installation instructions see [installing kubectl](https://kubernetes.io/docs/tasks/tools/#kubectl).
-
-## Download from the release
-
-Karmada provides `kubectl-karmada` plug-in download service since v0.9.0. You can choose proper plug-in version which fits your operator system form [karmada release](https://github.com/karmada-io/karmada/releases).
-
-Take v1.2.1 that working with linux-amd64 os as an example:
-
-```bash
-wget https://github.com/karmada-io/karmada/releases/download/v1.2.1/kubectl-karmada-linux-amd64.tgz
-
-tar -zxf kubectl-karmada-linux-amd64.tgz
+```
+helm repo add hami-charts https://project-hami.github.io/HAMi/
 ```
 
-Next, move `kubectl-karmada` executable file to `PATH` path, reference from [Installing kubectl plugins](https://kubernetes.io/docs/tasks/extend-kubectl/kubectl-plugins/#installing-kubectl-plugins).
+## Get your kubernetes version
 
-## Install using Krew
+kubenetes version is needed for properly installation. You can get this information by using the following command:
 
-Krew is the plugin manager for `kubectl` command-line tool.
+```
+kubectl version
+```
 
-[Install and set up](https://krew.sigs.k8s.io/docs/user-guide/setup/install/) Krew on your machine.
+## Installation
 
-Then install `kubectl-karmada` plug-in:
+During installation, set the Kubernetes scheduler image version to match your Kubernetes server version. For instance, if your cluster server version is 1.16.8, use the following command for deployment:
 
-```bash
-kubectl krew install karmada
+```
+helm install hami hami-charts/hami --set scheduler.kubeScheduler.imageTag=v1.16.8 -n kube-system
 ```
 
-You can refer to [Quickstart of Krew](https://krew.sigs.k8s.io/docs/user-guide/quickstart/) for more information.
+You can customize your installation by adjusting the [configs](../userguide/configure.md).
 
-## Build from source code
+## Verify your installation
 
-Clone karmada repo and run `make` cmd from the repository:
+You can verify your installation using the following command:
 
-```bash
-make kubectl-karmada
+```
+kubectl get pods -n kube-system
 ```
 
-Next, move the `kubectl-karmada` executable file under the `_output` folder in the project root directory to the `PATH` path.
+If both hami-device-plugin and hami-scheduler pods are in the Running state, your installation is successful.

versioned_docs/version-v1.3.0/userguide/Cambricon-device/enable-cambricon-mlu-sharing.md

@@ -34,9 +34,11 @@ title: Enable cambricon MLU sharing
 
 * Install the chart using helm, See 'enabling vGPU support in kubernetes' section [here](https://github.com/Project-HAMi/HAMi#enabling-vgpu-support-in-kubernetes)
 
-* Tag MLU node with the following command
+* Activate the smlu mode for each MLUs on that node
 ```
-kubectl label node {mlu-node} mlu=on
+cnmon set -c 0 -smlu on
+cnmon set -c 1 -smlu on
+...
 ```
 
 ## Running MLU jobs

versioned_docs/version-v1.3.0/userguide/Cambricon-device/examples/allocate-core-and-memory.md

@@ -0,0 +1,36 @@
+---
+title: Allocate device core and memory resource
+---
+
+## Allocate device core and memory to container
+
+To allocate a certain part of device core resource, you need only to assign the `cambricon.com/mlu370.smlu.vmemory` and `cambricon.com/mlu370.smlu.vcore` along with the number of cambricon MLUs you requested in the container using `cambricon.com/vmlu`
+
+```
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: binpack-1
+  labels:
+    app: binpack-1
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: binpack-1
+  template:
+    metadata:
+      labels:
+        app: binpack-1
+    spec:
+      containers:
+        - name: c-1
+          image: ubuntu:18.04
+          command: ["sleep"]
+          args: ["100000"]
+          resources:
+            limits:
+              cambricon.com/vmlu: "1"
+              cambricon.com/mlu370.smlu.vmemory: "20"
+              cambricon.com/mlu370.smlu.vcore: "10"
+```

versioned_docs/version-v1.3.0/userguide/Cambricon-device/examples/allocate-exclusive.md

@@ -0,0 +1,34 @@
+---
+title: Allocate exclusive device
+---
+
+## Allocate exclusive device
+
+To allocate a whole cambricon device, you need to only assign `cambricon.com/vmlu` without other fields.
+
+```
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: binpack-1
+  labels:
+    app: binpack-1
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: binpack-1
+  template:
+    metadata:
+      labels:
+        app: binpack-1
+    spec:
+      containers:
+        - name: c-1
+          image: ubuntu:18.04
+          command: ["sleep"]
+          args: ["100000"]
+          resources:
+            limits:
+              cambricon.com/vmlu: "1" #allocates a whole MLU
+```

versioned_docs/version-v1.3.0/userguide/Device-supported.md

@@ -0,0 +1,14 @@
+---
+title: Device supported by HAMi
+---
+
+The view of device supported by HAMi is shown in this table below:
+
+| Production  | manufactor | Type        |MemoryIsolation | CoreIsolation | MultiCard support |
+|-------------|------------|-------------|-----------|---------------|-------------------|
+| GPU         | NVIDIA     | All         | ✅              | ✅            | ✅                |
+| MLU         | Cambricon  | 370, 590    | ✅              | ❌            | ❌                |
+| DCU         | Hygon      | Z100, Z100L | ✅              | ✅            | ❌                |
+| Ascend      | Huawei     | 910B        | ✅              | ✅            | ❌                |
+| GPU         | iluvatar   | All         | ✅              | ✅            | ❌                |
+| DPU         | Teco       | Checking    | In progress     | In progress   | ❌                |

versioned_sidebars/version-v1.3.0-sidebars.json

@@ -36,7 +36,7 @@
       "label": "User Guide",
       "items": [
         "version-v1.3.0/userguide/configure",
-        "version-v1.3.0/userguide/support-devices",
+        "version-v1.3.0/userguide/Device-supported",
         {
           "type": "category",
           "label": "Monitoring",
@@ -78,7 +78,8 @@
               "type": "category",
               "label": "Examples",
               "items": [
-                "version-v1.3.0/userguide/monitoring/globalview"
+                "version-v1.3.0/userguide/Cambricon-device/examples/allocate-core-and-memory",
+                "version-v1.3.0/userguide/Cambricon-device/examples/allocate-exclusive"
               ]
             }
           ]