# k0rdent（Mirantis）日跟踪 · 2026-09-11
> 日期：2026-09-11（Asia/Shanghai）。原料：archive/2026-09-11/k0rdent/。上一日成功日跟踪 2026-09-10。

## 摘要
- **本日无公开战略级新稿**（无新日期通稿/版本号）。
- **产品页刷新（非战略通稿）**：`/ai-platform-as-a-service/` 抽取正文较昨日变长，出现 **Turnkey Inference** 叙事（vLLM / Triton / KServe / RayServe 等编目 + Smart Routing）；仍是营销页片段，含 `undefined` 噪声——**不作档案版本字段变更**。
- **续档仍有效**：NVIDIA-Certified Hypervisor（GB200 NVL72）、Metal-to-Model / AI PaaS。
- IREN 相关 GlobeNewswire URL 本日仍失败（空正文 0 字节）——**勿用空归档当引用**。
- 定位不变：K8s 原生 AI 控制面 / GPU 云，不是 HCI 换芯。

## 原文摘录

### [k0rdent AI: NVIDIA-Certified Hypervisor on GB200 NVL72](https://www.mirantis.com/blog/mirantis-k0rdent-ai-certified-through-the-nvidia-certified-hypervisors-program/) · 续档
- 归档：`k0rdent/k0rdent-ai-nvidia-certified-hypervisor-on-gb200-nvl72-1be5ef71.txt`
- URL：https://www.mirantis.com/blog/mirantis-k0rdent-ai-certified-through-the-nvidia-certified-hypervisors-program/
> As an inaugural ISV partner in the NVIDIA-Certified Hypervisors program, Mirantis has achieved NVIDIA certification for k0rdent AI's virtualization stack, which delivers predictable, bare metal-like performance on NVIDIA GB200 NVL72 with NVIDIA Grace CPUs.

### [Mirantis k0rdent AI PaaS](https://www.mirantis.com/ai-platform-as-a-service/) · 续档（页文案刷新）
- 归档：`k0rdent/mirantis-k0rdent-ai-paas-monetize-and-modernize-ai-clouds-9fc1eb94.txt`
- URL：https://www.mirantis.com/ai-platform-as-a-service/
> Turnkey Inference: Configure and lifecycle manage complete inference service stacks… assemble inference solutions from a fast-growing catalog of operations frameworks (e.g., Run.ai, KubeRay, Gcore…) , model servers (e.g. vLLM, Triton, KServe, RayServe, etc.)…

## 对基础档案的影响
- NVIDIA 认证 / AI PaaS 续档维持；Turnkey Inference 仅为产品页抽取增强，本日不改档案「最近动态」。