docs: add blog post and lab guide for Volcano + HAMi-core soft slicing

i18n/zh/docusaurus-plugin-content-blog/hami-meetup-beijing-2025/index.md

@@ -5,6 +5,7 @@ description: "12 月 27 日，HAMi Meetup 北京站近百位技术伙伴齐聚
 authors: [hami_community]
 tags: ["HAMi", "Meetup", "异构算力", "GPU 虚拟化", "云原生"]
 image: "./hami-meetup-beijing-banner.webp"
+unlisted: true
 ---
 
 ![HAMi Meetup 北京站](hami-meetup-beijing-banner.webp)

i18n/zh/docusaurus-plugin-content-blog/hami-meetup-shanghai-2025/index.md

@@ -6,6 +6,7 @@ image: ./meetup-banner.png
 tags:
   ["Meetup", "上海", "异构算力调度", "GPU 虚拟化", "Kubernetes", "国产算力", "AI 训练与推理优化"]
 authors: [hami_community]
+unlisted: true
 ---
 
 11 月 30 日，首场 HAMi Meetup 在上海圆满结束。本次活动以"不卷算力卷效率"为主题，近百位 AI 开发者、运维工程师、企业 IT 架构师齐聚现场，聚焦异构算力调度的核心命题。

i18n/zh/docusaurus-plugin-content-blog/hami-meetup-shenzhen-2026/index.md

@@ -5,6 +5,7 @@ description: "4 月 25 日，HAMi Meetup 深圳站成功举办。来自 CNCF、
 image: ./meetup-shenzhen-group-photo.webp
 tags: ["HAMi", "Meetup", "深圳", "GPU 虚拟化", "异构算力调度", "DRA", "云原生", "AI 基础设施"]
 authors: [hami_community]
+unlisted: true
 ---
 
 ![HAMi Meetup 深圳站](meetup-shenzhen-group-photo.webp)

i18n/zh/docusaurus-plugin-content-blog/tags.yml

@@ -82,6 +82,18 @@
 "NVIDIA":
   label: "NVIDIA"
   permalink: "/nvidia"
+"Volcano":
+  label: "Volcano"
+  permalink: "/volcano"
+"Ascend":
+  label: "Ascend"
+  permalink: "/ascend"
+"vNPU":
+  label: "vNPU"
+  permalink: "/v-npu"
+"软切分":
+  label: "软切分"
+  permalink: "/soft-slicing"
 "Release":
   label: "Release"
   permalink: "/release"

i18n/zh/docusaurus-plugin-content-docs-tutorials/current/overview.md

@@ -19,4 +19,4 @@ import LabCardGridAuto from '@site/src/components/labs/LabCardGridAuto';
 
 <LabCardGridAuto />
 
-每个实验都列出了各自的前提条件。实验 3 和 4 直接复用实验 1 搭建的集群，一次开机即可完成全部三个实验；实验 2 可在任意笔记本上运行，无需 GPU。实验 7 在租用的 GPU 虚拟机上自行搭建单节点 k3s 集群，不使用 GPU Operator。实验 8 需要已有的 Volcano GPU 集群，用于验证 Volcano vGPU、Gang 调度和队列级资源限制。实验 9 使用 Kueue 准入控制限制 HAMi vGPU 数量、显存和算力配额。实验 11 将从头搭建完整的 KServe Standard 推理环境，并通过 HAMi 原生 DRA Claim 让两个 vLLM 副本共享一张 GPU。实验 12 在 GKE 1.35/COS/CDI 上部署 KAI Scheduler 与 HAMi-core，并通过 CUDA 分配验证显存上限。
+每个实验都列出了各自的前提条件。实验 3 和 4 直接复用实验 1 搭建的集群，一次开机即可完成全部三个实验；实验 2 可在任意笔记本上运行，无需 GPU。实验 7 在租用的 GPU 虚拟机上自行搭建单节点 k3s 集群，不使用 GPU Operator。实验 8 需要已有的 Volcano GPU 集群，用于验证 Volcano vGPU、Gang 调度和队列级资源限制。实验 9 使用 Kueue 准入控制限制 HAMi vGPU 数量、显存和算力配额。实验 11 将从头搭建完整的 KServe Standard 推理环境，并通过 HAMi 原生 DRA Claim 让两个 vLLM 副本共享一张 GPU。实验 12 在 GKE 1.35/COS/CDI 上部署 KAI Scheduler 与 HAMi-core，并通过 CUDA 分配验证显存上限。实验 13 在昇腾 310P3 ARM 服务器上源码编译 Volcano 与 ascend-device-plugin，验证 hami-vnpu-core 软切分、binpack 共卡与容器级监控指标。

i18n/zh/docusaurus-plugin-content-docs-tutorials/current/tags.yml

@@ -1,6 +1,9 @@
 "DRA":
   label: "DRA"
   permalink: "/dra"
+"ascend":
+  label: "Ascend"
+  permalink: "/ascend"
 "GPU 分区":
   label: "GPU 分区"
   permalink: "/gpu-partitioning"
@@ -55,6 +58,9 @@
 "topology":
   label: "topology"
   permalink: "/topology"
+"vnpu":
+  label: "vNPU"
+  permalink: "/vnpu"
 "vgpu":
   label: "vgpu"
   permalink: "/vgpu"
@@ -82,6 +88,9 @@
 "资源共享":
   label: "资源共享"
   permalink: "/resource-sharing"
+"soft-slicing":
+  label: "软切分"
+  permalink: "/soft-slicing"
 "隔离":
   label: "隔离"
   permalink: "/isolation"

sidebars-tutorials.js

@@ -71,6 +71,11 @@ module.exports = {
           id: "labs/kai-scheduler-hami-gke",
           customProps: { level: "Advanced", duration: "about 90 minutes" },
         },
+        {
+          type: "doc",
+          id: "labs/volcano-ascend-vnpu",
+          customProps: { level: "Advanced", duration: "about 120 minutes" },
+        },
       ],
     },
   ],

tutorials/labs/examples/13-volcano-ascend-vnpu/01-volcano-scheduler-configmap.yaml

@@ -0,0 +1,30 @@
+# Volcano scheduler configuration with the deviceshare plugin in HAMi vNPU mode.
+# Apply into volcano-system, then: kubectl -n volcano-system rollout restart deploy volcano-scheduler
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: volcano-scheduler-configmap
+  namespace: volcano-system
+data:
+  volcano-scheduler.conf: |
+    actions: "enqueue, allocate, backfill"
+    tiers:
+      - plugins:
+          - name: priority
+          - name: gang
+            enablePreemptable: false
+          - name: conformance
+      - plugins:
+          - name: overcommit
+          - name: drf
+            enablePreemptable: false
+          - name: predicates
+          - name: deviceshare
+            arguments:
+              deviceshare.AscendHAMiVNPUEnable: "true"
+              deviceshare.SchedulePolicy: binpack
+              deviceshare.KnownGeometriesCMNamespace: kube-system
+              deviceshare.KnownGeometriesCMName: hami-scheduler-device
+          - name: proportion
+          - name: nodeorder
+          - name: binpack

tutorials/labs/examples/13-volcano-ascend-vnpu/02-hami-device-node-config.yaml

@@ -0,0 +1,22 @@
+# Per-node HAMi device plugin configuration: enable hami-vnpu-core on one node.
+# Replace "aio-node74-arm" with your Ascend node name. vDeviceCount is the
+# per-card vNPU count, honored directly by the plugin (since v1.4.0); 7 matches
+# the 310P3 capacity verified in this lab.
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  labels:
+    app.kubernetes.io/component: hami-scheduler
+    app.kubernetes.io/name: hami
+    app.kubernetes.io/instance: hami
+  name: hami-device-node-config
+  namespace: kube-system
+data:
+  node-config.yaml: |-
+    nodes:
+      - name: "aio-node74-arm"
+        hami-vnpu-core: true
+        vDeviceCount: 7
+        filterDevices:
+          index: []
+          uuid: []

tutorials/labs/examples/13-volcano-ascend-vnpu/03-ascend-vnpu-check.yaml

@@ -0,0 +1,18 @@
+# First soft-sliced vNPU Pod: 1 vNPU with an 8192 MiB memory slice.
+apiVersion: v1
+kind: Pod
+metadata:
+  name: ascend-vnpu-check
+  annotations:
+    huawei.com/vnpu-mode: hami-core
+spec:
+  schedulerName: volcano
+  runtimeClassName: ascend
+  containers:
+    - name: npu
+      image: quay.io/ascend/vllm-ascend:v0.18.0-310p
+      command: ["sleep", "infinity"]
+      resources:
+        limits:
+          huawei.com/Ascend310P: "1"
+          huawei.com/Ascend310P-memory: "8192"

tutorials/labs/examples/13-volcano-ascend-vnpu/04-ascend-vnpu-check-2.yaml

@@ -0,0 +1,19 @@
+# Second soft-sliced vNPU Pod, identical to the first: with the binpack policy
+# it lands on the same physical card as ascend-vnpu-check.
+apiVersion: v1
+kind: Pod
+metadata:
+  name: ascend-vnpu-check-2
+  annotations:
+    huawei.com/vnpu-mode: hami-core
+spec:
+  schedulerName: volcano
+  runtimeClassName: ascend
+  containers:
+    - name: npu
+      image: quay.io/ascend/vllm-ascend:v0.18.0-310p
+      command: ["sleep", "infinity"]
+      resources:
+        limits:
+          huawei.com/Ascend310P: "1"
+          huawei.com/Ascend310P-memory: "8192"