{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-07-23T07:21:26.498Z","headline":"Ray 2.55 正式支持 Google Cloud TPU，通过 KubeRay 自动编排多主机切片","description":"Ray 2.55 首次为 Google Cloud TPU 提供一等支持，开发者可通过 Ray 任务与 Actor API 在 TPU 上运行分布式 Python 负载。","url":"https://www.aioga.com/news/cmrth189u36hobitl8fiuyu4z/","mainEntityOfPage":"https://www.aioga.com/news/cmrth189u36hobitl8fiuyu4z/","datePublished":"2026-07-20T16:59:54.801Z","dateModified":"2026-07-20T16:59:54.801Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://developers.googleblog.com/run-ray-on-tpu-part-1-the-foundations","https://aihot.virxact.com/items/cmrth189u36hobitl8fiuyu4z"],"canonicalUrl":"https://www.aioga.com/news/cmrth189u36hobitl8fiuyu4z/","directAnswer":{"@type":"Answer","text":"Aioga 编辑摘要：Ray 2.55 首次为 Google Cloud TPU 提供一等支持，开发者可通过 Ray 任务与 Actor API 在 TPU 上运行分布式 Python 负载。 Aioga 将其归入「产品更新」方向，重点关注它对真实使用和行业竞争的影响。","url":"https://www.aioga.com/news/cmrth189u36hobitl8fiuyu4z/","dateCreated":"2026-07-20T16:59:54.801Z","author":{"@type":"Organization","@id":"https://www.aioga.com/authors/aioga-editorial/#editorial-team","name":"Aioga Editorial Team","url":"https://www.aioga.com/authors/aioga-editorial/"}},"evidence":[{"@type":"CreativeWork","name":"developers.googleblog.com source article","url":"https://developers.googleblog.com/run-ray-on-tpu-part-1-the-foundations","datePublished":"2026-07-20T16:59:54.801Z","provider":{"@type":"Organization","name":"developers.googleblog.com","url":"https://developers.googleblog.com/run-ray-on-tpu-part-1-the-foundations"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.virxact.com/items/cmrth189u36hobitl8fiuyu4z","datePublished":"2026-07-20T16:59:54.801Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.virxact.com/items/cmrth189u36hobitl8fiuyu4z"}}],"aggregationSource":"Google Developers Blog（RSS）","originalPublisher":{"name":"developers.googleblog.com","url":"https://developers.googleblog.com/run-ray-on-tpu-part-1-the-foundations"},"article":{"id":"cmrth189u36hobitl8fiuyu4z","slug":"cmrth189u36hobitl8fiuyu4z","url":"https://www.aioga.com/news/cmrth189u36hobitl8fiuyu4z/","title":"Ray 2.55 正式支持 Google Cloud TPU，通过 KubeRay 自动编排多主机切片","title_en":"Run Ray on TPU， Part 1： The foundations","summary":"Ray 2.55 首次为 Google Cloud TPU 提供一等支持，开发者可通过 Ray 任务与 Actor API 在 TPU 上运行分布式 Python 负载。","source":"Google Developers Blog（RSS）","sourceUrl":"https://developers.googleblog.com/run-ray-on-tpu-part-1-the-foundations","aiHotUrl":"https://aihot.virxact.com/items/cmrth189u36hobitl8fiuyu4z","publishedAt":"2026-07-20T16:59:54.801Z","category":"产品更新","score":56,"selected":false,"articleBody":["TL;DR : If you already scale Python with Ray on GPUs, your code can now run on TPU (Tensor Processing Unit, Google's AI accelerator chip) with fully supported official APIs you already know. The task-and-actor model, a JaxTrainer, the same Ray Serve deployment just pointed at TPUs orchestrated by Google Kubernetes Engine (GKE).","As of Ray 2.55, Google Cloud TPUs are a first-class accelerator in Ray . This means that TPUs are now in Ray's release pipelines with official pre-built images and support across the core libraries, instead of the old \"experimental\" path where you built your own containers and leaned on community help. In this \"Run Ray on TPU\" series, you will learn how a TPU slice is just another accelerator Ray schedules onto (Part 1), then walk through each library (Part 2).","Ray is a distributed-computing framework: you write Python, and Ray runs it across a cluster as tasks (stateless functions) and actors (stateful workers). To Ray, a TPU is just another schedulable resource, the way a GPU is. You ask for it, Ray places your work on it.","But there is one thing to keep in mind, and then we move on.","TPU chips are wired together into a fixed group called a slice : several host machines (VMs) whose chips share a dedicated high-speed link called the ICI (Inter-Chip Interconnect). A multi-host model has to land on one whole slice , or its workers can't reach each other and the job just hangs.","If you think in GPUs, picture a slice as a single multi-GPU box where the fast interconnect (NVLink) only exists inside the box. Split your workers across two boxes with no cable between them and the collective operations, the all-reduce steps that synchronize gradients, never finish. Training just hangs. A TPU slice behaves the same way: the ICI is that cable, and it only reaches the chips of one slice.","That's the whole reason \"Ray on TPU\" needs anything special. Something has to guarantee all your workers land on one intact slice. On GPUs you barely think about it; on TPUs it's crucial, and Ray and GKE (Google Kubernetes Engine, Google's managed Kubernetes) handle it for you.","One more word you'll see everywhere is topology : it's the shape of a slice, written like 4x4 for a 16-chip slice. You ask for a topology, not a chip count.","Once you understand slicing and topology with TPU, the existing Ray stack and your development process remains unchanged and it runs on TPU slices that GKE provisions. The diagram below is the whole system in one picture: on the left, the code you write (the Ray libraries you already use); in the middle, the Ray Core layer that reserves whole slices; on the right, the GKE managed layer that provisions the hardware and labels it so Ray can find slice boundaries.","GKE provisions a slice and labels its hosts, Ray Core reads those labels to reserve the whole slice at once, and your library call sits on top, declaring a topology and nothing more. No hand-written placement code anywhere. The rest of this part walks the bottom two layers, GKE then Ray Core while Part 2 covers the Ray AI libraries.","You run Ray on TPU through GKE using the Ray Operator add-on .","That single flag installs two things that matter for TPU. The first, KubeRay , is the Kubernetes operator that turns RayCluster, RayService, and RayJob YAML into running Ray clusters; it's the same KubeRay you'd use with GPUs. The second is the TPU-specific part: the Ray TPU webhook , which stamps every TPU host with labels like ray.io/tpu-slice-name so Ray can tell which machines are wired into the same slice. That label is the thread the whole system pulls on.","From there, you ask for TPUs in a manifest the same way you'd ask for any node, with a nodeSelector for the generation and topology and the chip count as a resource. A multi-host slice adds one field, numOfHosts.","GKE provisions the slice, the webhook labels it, Ray reads the labels. You write Python. Once the add-on is up, you'll see the KubeRay operator pod running, and applying that manifest brings up a head pod plus one worker pod per host in the slice. The cluster step：https://github.com/GoogleCloudPlatform/kubernetes-engine-samples/tree/main/ai-ml/gke-ray/tpu/get-started/cluster of the get-started example provisions all of this with Terraform.","What actually keeps your workers together is a Ray Core primitive sitting just above this layer, the slice placement group , and that's where the rest of the guide starts.","Ray Core is the base layer, the task-and-actor engine and scheduler everything else sits on. Its TPU support lives in the public ray.util.tpu API, and there's really one function to know: slice_placement_group() . It takes that \"keep my workers on one intact slice\" guarantee from earlier and turns it into a single call, reserving a whole slice atomically (all hosts or none) by matching on the webhook labels.","It is important to highlight that you rarely call slice_placement_group yourself. The Ray AI libraries (Data, Train, Serve) call it for you, so in practice you declare a topology and they handle the slice. You'd only reach for slice_placement_group() directly when you're writing a custom distributed workload that isn't Train, Serve, or Data. One caveat worth knowing: the API is public but marked alpha ( @PublicAPI(stability=\"alpha\") ), so it's usable today but the surface can still shift between releases.","You now have the whole mental model: a slice has to stay intact, GKE provisions and labels it, and Ray Core reserves it as a unit so you never hand-write placement code. Everything you actually build sits on top of that and reuses it.","In Part 2, we will explore how you can use Ray AI libraries on TPU for serving LLMs with vLLM, feeding slices with Ray Data and training with JaxTrainer.","For now, thanks for reading! And if you have any additional questions or feedback, feel free to reach out on socials (LinkedIn：https://www.linkedin.com/in/ivan-nardini, X：https://x.com/ivnardini).","Expanding Choice in Gemini Enterprise Agent Platform: Introducing Grounding with Parallel Web Search","Building scalable AI agents with modular prompt transpilation","Driving the Agent Quality Flywheel from Your Coding Agent"],"articleImages":[{"sourceUrl":"https://storage.googleapis.com/gweb-developer-goog-blog-cms-assets/site/20260519-162827/images/g-dev.svg","alt":"Google for Developers","afterParagraph":0,"url":"/media/articles/cmrth189u36hobitl8fiuyu4z/8d66d7423366f696.jpg"},{"sourceUrl":"https://storage.googleapis.com/gweb-developer-goog-blog-assets/images/header.original_nhYbgwk.png","alt":"header","afterParagraph":0,"url":"/media/articles/cmrth189u36hobitl8fiuyu4z/6610830e4f4b0789.png"},{"sourceUrl":"https://storage.googleapis.com/gweb-developer-goog-blog-assets/images/fig1_2.original.png","alt":"fig1 (2)","afterParagraph":5,"url":"/media/articles/cmrth189u36hobitl8fiuyu4z/fd24e1cae290112d.png"},{"sourceUrl":"https://storage.googleapis.com/gweb-developer-goog-blog-assets/images/fig2_2.original.png","alt":"fig2 (2)","afterParagraph":8,"url":"/media/articles/cmrth189u36hobitl8fiuyu4z/ba51b12b80d7bb74.png"},{"sourceUrl":"https://storage.googleapis.com/gweb-developer-goog-blog-assets/images/flywheel-blog-hero-image.2e16d0ba.fill-800x400.png","alt":"Driving the Agent Quality Flywheel from Your Coding Agent","afterParagraph":21,"url":"/media/articles/cmrth189u36hobitl8fiuyu4z/659a34e4790fb31e.png"}],"mediaStatus":"ok","articleBodyZh":["总结：DR：如果你已经在GPU上用Ray扩展Python，你的代码现在可以在TPU（Tensor Processing Unit，谷歌的AI加速芯片）上运行，并且你已经知道完全支持官方API。任务与角色模型、JaxTrainer、同样的Ray Serve部署，只是指向由Google Kubernetes Engine（GKE）编排的TPU。","截至Ray 2.55，Google Cloud TPU已成为Ray的顶级加速器。这意味着TPU现在已经进入Ray的发布流程，拥有官方预构建的镜像，核心库支持，而不是过去那种“实验性”路径，自己构建容器并依赖社区帮助。在本“Run Ray on TPU”系列中，你将学习TPU切片如何成为Ray调度的另一个加速器（第一部分），然后逐一了解每个库（第二部分）。","Ray 是一个分布式计算框架：你编写 Python，Ray 将其作为任务（无状态函数）和演员（有状态工作者）在集群中运行。对Ray来说，TPU只是另一个可调度的资源，就像GPU一样。你要求，雷就把你的作品放上去。","但有一点要记住，然后我们就继续前进。","TPU芯片被布线成一个固定的组，称为切片：多个主机（VM），这些主机的芯片共享一个专用的高速链路，称为ICI（芯片间互连）。多主机模型必须停在一个完整的切片上，否则其工人无法相互联系，工作就会卡住。","如果你把GPU想象成一个单一的多GPU盒子，快速互连（NVLink）只存在于盒子内部。把员工分成两个箱子，中间没有电缆，集体操作——同步梯度的全减步骤——永远不会完成。训练只是悬而未决。TPU片的行为方式相同：ICI就是那根线缆，它只连接到其中一片片的芯片。","这正是《Ray on TPU》需要特别内容的全部原因。必须有某种方式保证所有工人都能落在一片完整的片上。在显卡上你几乎不会多想;在TPU上这点至关重要，Ray和GKE（Google Kubernetes Engine，谷歌托管的Kubernetes）帮你处理。","你到处都会看到一个词，那就是拓扑学：它指的是切片的形状，写成4x4，代表16芯片的切片。你要的是拓扑结构，而不是芯片数。","一旦你理解了 TPU 的切片和拓扑，现有的 Ray 栈和你的开发流程将保持不变，并且它会在 GKE 提供的 TPU 切片上运行。下图展示了整个系统的一张图：左侧是你编写的代码（你已经使用的 Ray 库）；中间是 Ray Core 层，它保留了整片切片；右侧是 GKE 管理层，它提供硬件并标记，使 Ray 能够找到切片边界。","GKE 提供一个切片并标记其主机，Ray Core 读取这些标签以一次性保留整个切片，而你的库调用位于最上层，仅声明拓扑而不做其他操作。无任何手写的放置代码。本部分其余内容讲解底部的两层，先 GKE 再 Ray Core，而第二部分涵盖 Ray AI 库。","你通过 GKE 使用 Ray Operator 插件在 TPU 上运行 Ray。","该单一标志安装两个对 TPU 至关重要的组件。首先，KubeRay，是 Kubernetes 操作器，将 RayCluster、RayService 和 RayJob YAML 转换为运行中的 Ray 集群；它与使用 GPU 时的 KubeRay 相同。第二是 TPU 特定部分：Ray TPU webhook，它会为每台 TPU 主机打上 ray.io/tpu-slice-name 等标签，以便 Ray 能够识别哪些机器连接在同一切片上。这个标签是整个系统运行的关键线索。","之后，你在清单中请求 TPU，就像请求任何节点一样，通过 nodeSelector 指定代数和拓扑，并将芯片数量作为资源。多主机切片增加一个字段 numOfHosts。","GKE 提供切片，webhook 给它打标签，Ray 读取标签。你编写 Python 代码。一旦插件启动，你将看到 KubeRay 操作器 Pod 正在运行，应用该清单会启动一个 head pod 加上切片中每台主机各一个 worker pod。示例的 get-started 集群步骤：https://github.com/GoogleCloudPlatform/kubernetes-engine-samples/tree/main/ai-ml/gke-ray/tpu/get-started/cluster 使用 Terraform 提供了所有这些。","真正将你的工作节点聚集在一起的是 Ray Core 原语，位于此层之上，即切片放置组，也是本指南其余部分的起点。","Ray Core 是基础层，是任务与执行引擎及调度器的一切依托。它的 TPU 支持存在于公共的 ray.util.tpu API 中，实际上只有一个函数需要了解：slice_placement_group()。它将之前提到的“保持我的工作节点在一个完整切片中”的保证转化为一个单独的调用，通过匹配 webhook 标签以原子方式（所有主机或者全无）预留整个切片。","需要强调的是，你很少会自己调用 slice_placement_group。Ray AI 库（Data、Train、Serve）会为你调用它，因此在实践中，你只需声明拓扑，它们会处理切片。你只会在编写自定义分布式工作负载（不是 Train、Serve 或 Data）时直接使用 slice_placement_group()。值得注意的一点是：该 API 是公开的，但标记为 alpha（@PublicAPI(stability=\"alpha\")），所以目前可用，但接口在各版本之间仍可能发生变化。","现在你已经掌握了完整的思维模型：切片必须保持完整，GKE 提供并标记它，而 Ray Core 将其作为一个单位进行预留，因此你永远不需要手写放置代码。你实际构建的所有内容都建立在它之上并重用它。","在第二部分中，我们将探讨如何在 TPU 上使用 Ray AI 库通过 vLLM 提供 LLM 服务，利用 Ray Data 提供切片，并使用 JaxTrainer 进行训练。","目前，感谢阅读！如果你有任何额外的问题或反馈，欢迎通过社交平台联系我（LinkedIn：https://www.linkedin.com/in/ivan-nardini，X：https://x.com/ivnardini）。","在 Gemini Enterprise Agent 平台扩展选择：引入带并行网页搜索的 Grounding 功能","通过模块化提示转换构建可扩展的 AI 代理","用你的编码代理推动代理质量飞轮"],"translationStatus":"translated","bodyOrigin":"source-page","editorial":{"summary":"Aioga 编辑摘要：Ray 2.55 首次为 Google Cloud TPU 提供一等支持，开发者可通过 Ray 任务与 Actor API 在 TPU 上运行分布式 Python 负载。 Aioga 将其归入「产品更新」方向，重点关注它对真实使用和行业竞争的影响。","background":"背景分析：产品与工具类动态的价值取决于它是否解决明确场景、能否进入工作流，以及交付、价格和数据安全是否可接受。","viewpoint":"Aioga 判断：这条动态更适合作为行业观察信号，当前信息足以建立线索，但不足以推导长期结论。","implications":"影响分析：对相关团队而言，短期应先核对来源、可用范围和实际成本，再判断是否值得接入或跟进。","nextStep":"后续观察：继续观察产品是否开放使用、用户反馈、定价、集成能力和后续版本更新。","evidenceRefs":["title","summary","articleBody"],"confidence":"medium","status":"published","aiGenerated":false,"autoApproved":true,"generatedBy":"rule-safe-fallback","generatedAt":"2026-07-23T07:30:40.523Z","sourceHash":"048b0381a71349d1","validation":{"passed":true,"mode":"rule-safe-fallback","checks":["schema","length","source-attribution","no-html"]}},"tags":["产品更新","Google Developers Blog（RSS）"],"translations":{"zh-CN":{"title":"Ray 2.55 正式支持 Google Cloud TPU，通过 KubeRay 自动编排多主机切片","summary":"Ray 2.55 首次为 Google Cloud TPU 提供一等支持，开发者可通过 Ray 任务与 Actor API 在 TPU 上运行分布式 Python 负载。","category":"产品更新","source":"developers.googleblog.com","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55 正式支持 Google Cloud TPU，通过 KubeRay 自动编排多主机切片 - Aioga AI资讯","description":"Ray 2.55 首次为 Google Cloud TPU 提供一等支持，开发者可通过 Ray 任务与 Actor API 在 TPU 上运行分布式 Python 负载。","url":"https://www.aioga.com/news/cmrth189u36hobitl8fiuyu4z/"},"en":{"title":"Ray 2.55 officially supports Google Cloud TPU, orchestrating multi-host slices automatically through KubeRay","summary":"Ray 2.55 provides first-class support for Google Cloud TPU for the first time, allowing developers to run distributed Python workloads on TPU through Ray tasks and Actor API.","category":"Products","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55 officially supports Google Cloud TPU, orchestrating multi-host slices automatically through KubeRay - Aioga AI News","description":"Ray 2.55 provides first-class support for Google Cloud TPU for the first time, allowing developers to run distributed Python workloads on TPU through Ray tasks and Actor API.","url":"https://www.aioga.com/en/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:21:36.622Z"},"ja":{"title":"Ray 2.55 は公式に Google Cloud TPU をサポートし、KubeRay を通じてマルチホストのシャーディングを自動でオーケストレーションします","summary":"Ray 2.55 は初めて Google Cloud TPU に一流のサポートを提供し、開発者は Ray のタスクと Actor API を通じて TPU 上で分散 Python ワークロードを実行できるようになった。","category":"製品更新","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55 は公式に Google Cloud TPU をサポートし、KubeRay を通じてマルチホストのシャーディングを自動でオーケストレーションします - Aioga AIニュース","description":"Ray 2.55 は初めて Google Cloud TPU に一流のサポートを提供し、開発者は Ray のタスクと Actor API を通じて TPU 上で分散 Python ワークロードを実行できるようになった。","url":"https://www.aioga.com/ja/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:21:48.798Z"},"ko":{"title":"Ray 2.55는 공식적으로 Google Cloud TPU를 지원하며, KubeRay를 통해 다중 호스트 조각을 자동으로 오케스트레이션합니다","summary":"Ray 2.55는 처음으로 Google Cloud TPU에 대한 일등 지원을 제공하며, 개발자는 Ray 작업과 Actor API를 통해 TPU에서 분산 Python 작업을 실행할 수 있습니다.","category":"제품 업데이트","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55는 공식적으로 Google Cloud TPU를 지원하며, KubeRay를 통해 다중 호스트 조각을 자동으로 오케스트레이션합니다 - Aioga AI 뉴스","description":"Ray 2.55는 처음으로 Google Cloud TPU에 대한 일등 지원을 제공하며, 개발자는 Ray 작업과 Actor API를 통해 TPU에서 분산 Python 작업을 실행할 수 있습니다.","url":"https://www.aioga.com/ko/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:22:31.405Z"},"es":{"title":"Ray 2.55 admite oficialmente Google Cloud TPU y orquesta automáticamente fragmentos de múltiples hosts a través de KubeRay","summary":"Ray 2.55 proporciona por primera vez soporte de primera clase para Google Cloud TPU, y los desarrolladores pueden ejecutar cargas de trabajo distribuidas de Python en TPU a través de las API de tareas y Actor de Ray.","category":"Productos","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55 admite oficialmente Google Cloud TPU y orquesta automáticamente fragmentos de múltiples hosts a través de KubeRay - Aioga Noticias de IA","description":"Ray 2.55 proporciona por primera vez soporte de primera clase para Google Cloud TPU, y los desarrolladores pueden ejecutar cargas de trabajo distribuidas de Python en TPU a través...","url":"https://www.aioga.com/es/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:22:29.448Z"},"fr":{"title":"Ray 2.55 prend officiellement en charge Google Cloud TPU, orchestrant automatiquement des tranches multi-hôtes via KubeRay","summary":"Ray 2.55 offre pour la première fois un support de premier ordre pour Google Cloud TPU, permettant aux développeurs d'exécuter des charges Python distribuées sur TPU via les API Ray Tasks et Actor.","category":"Produits","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55 prend officiellement en charge Google Cloud TPU, orchestrant automatiquement des tranches multi-hôtes via KubeRay - Aioga Actualités IA","description":"Ray 2.55 offre pour la première fois un support de premier ordre pour Google Cloud TPU, permettant aux développeurs d'exécuter des charges Python distribuées sur TPU via les API Ra...","url":"https://www.aioga.com/fr/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:23:12.835Z"},"de":{"title":"Ray 2.55 unterstützt offiziell Google Cloud TPU und orchestriert Multi-Host-Slices automatisch über KubeRay","summary":"Ray 2.55 bietet erstmals erstklassige Unterstützung für Google Cloud TPU, sodass Entwickler verteilte Python-Workloads über Ray Tasks und Actor API auf TPU ausführen können.","category":"产品更新","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55 unterstützt offiziell Google Cloud TPU und orchestriert Multi-Host-Slices automatisch über KubeRay - Aioga KI-News","description":"Ray 2.55 bietet erstmals erstklassige Unterstützung für Google Cloud TPU, sodass Entwickler verteilte Python-Workloads über Ray Tasks und Actor API auf TPU ausführen können.","url":"https://www.aioga.com/de/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:23:12.324Z"},"pt-BR":{"title":"Ray 2.55 oferece suporte oficial ao Google Cloud TPU, permitindo a orquestração automática de shards multi-host com KubeRay","summary":"Ray 2.55 oferece suporte de primeira classe para o Google Cloud TPU pela primeira vez, permitindo que os desenvolvedores executem cargas de trabalho Python distribuídas em TPUs através da API de Tarefas e de Atores do Ray.","category":"产品更新","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55 oferece suporte oficial ao Google Cloud TPU, permitindo a orquestração automática de shards multi-host com KubeRay - Aioga Notícias de IA","description":"Ray 2.55 oferece suporte de primeira classe para o Google Cloud TPU pela primeira vez, permitindo que os desenvolvedores executem cargas de trabalho Python distribuídas em TPUs atr...","url":"https://www.aioga.com/pt-BR/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:23:51.005Z"},"ru":{"title":"Ray 2.55 официально поддерживает Google Cloud TPU, через KubeRay автоматически оркестрируя многомашинные шардированные процессы","summary":"Ray 2.55 впервые предоставляет первоклассную поддержку Google Cloud TPU, разработчики могут использовать API задач и акторов Ray для выполнения распределённых Python-загрузок на TPU.","category":"产品更新","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55 официально поддерживает Google Cloud TPU, через KubeRay автоматически оркестрируя многомашинные шардированные процессы - Aioga Новости ИИ","description":"Ray 2.55 впервые предоставляет первоклассную поддержку Google Cloud TPU, разработчики могут использовать API задач и акторов Ray для выполнения распределённых Python-загрузок на TP...","url":"https://www.aioga.com/ru/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:23:52.400Z"},"ar":{"title":"Ray 2.55 يدعم رسميًا Google Cloud TPU، من خلال KubeRay يمكن تنظيم تقسيمات متعددة المضيفين تلقائيًا","summary":"يقدم Ray 2.55 لأول مرة دعمًا من الدرجة الأولى لـ Google Cloud TPU، حيث يمكن للمطورين تشغيل أحمال Python الموزعة على TPU من خلال واجهة برمجة تطبيقات المهام وActor الخاصة بـ Ray.","category":"产品更新","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55 يدعم رسميًا Google Cloud TPU، من خلال KubeRay يمكن تنظيم تقسيمات متعددة المضيفين تلقائيًا - Aioga أخبار الذكاء الاصطناعي","description":"يقدم Ray 2.55 لأول مرة دعمًا من الدرجة الأولى لـ Google Cloud TPU، حيث يمكن للمطورين تشغيل أحمال Python الموزعة على TPU من خلال واجهة برمجة تطبيقات المهام وActor الخاصة بـ Ray.","url":"https://www.aioga.com/ar/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:24:30.677Z"},"hi":{"title":"Ray 2.55 आधिकारिक रूप से Google Cloud TPU का समर्थन करता है, KubeRay के माध्यम से मल्टी-होस्ट शार्डिंग को स्वचालित रूप से व्यवस्थित करता है","summary":"Ray 2.55 पहली बार Google Cloud TPU के लिए प्रथम श्रेणी का समर्थन प्रदान करता है, डेवलपर्स Ray कार्य और Actor API के माध्यम से TPU पर वितरित Python लोड चला सकते हैं।","category":"产品更新","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55 आधिकारिक रूप से Google Cloud TPU का समर्थन करता है, KubeRay के माध्यम से मल्टी-होस्ट शार्डिंग को स्वचालित रूप से व्यवस्थित करता है - Aioga AI समाचार","description":"Ray 2.55 पहली बार Google Cloud TPU के लिए प्रथम श्रेणी का समर्थन प्रदान करता है, डेवलपर्स Ray कार्य और Actor API के माध्यम से TPU पर वितरित Python लोड चला सकते हैं।","url":"https://www.aioga.com/hi/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:24:36.105Z"},"it":{"title":"Ray 2.55 supporta ufficialmente Google Cloud TPU, orchestrando automaticamente le slice multi-host tramite KubeRay","summary":"Ray 2.55 fornisce per la prima volta supporto di primo livello per Google Cloud TPU, consentendo agli sviluppatori di eseguire carichi di lavoro Python distribuiti su TPU tramite le API Task e Actor di Ray.","category":"产品更新","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55 supporta ufficialmente Google Cloud TPU, orchestrando automaticamente le slice multi-host tramite KubeRay - Aioga Notizie IA","description":"Ray 2.55 fornisce per la prima volta supporto di primo livello per Google Cloud TPU, consentendo agli sviluppatori di eseguire carichi di lavoro Python distribuiti su TPU tramite l...","url":"https://www.aioga.com/it/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:25:16.703Z"},"nl":{"title":"Ray 2.55 ondersteunt officieel Google Cloud TPU en automatiseert multi-host slicing via KubeRay","summary":"Ray 2.55 biedt voor het eerst eersteklas ondersteuning voor Google Cloud TPU, waardoor ontwikkelaars gedistribueerde Python-lasten op TPU kunnen uitvoeren via de Ray-taken- en Actor-API.","category":"产品更新","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55 ondersteunt officieel Google Cloud TPU en automatiseert multi-host slicing via KubeRay - Aioga AI-nieuws","description":"Ray 2.55 biedt voor het eerst eersteklas ondersteuning voor Google Cloud TPU, waardoor ontwikkelaars gedistribueerde Python-lasten op TPU kunnen uitvoeren via de Ray-taken- en Acto...","url":"https://www.aioga.com/nl/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:25:12.144Z"},"tr":{"title":"Ray 2.55, KubeRay aracılığıyla çoklu ana bilgisayar dilimlemeyi otomatik olarak düzenleyerek Google Cloud TPU'yu resmi olarak destekliyor","summary":"Ray 2.55, Google Cloud TPU için ilk kez birinci sınıf destek sunuyor; geliştiriciler, Ray görevleri ve Actor API aracılığıyla TPU üzerinde dağıtılmış Python yüklerini çalıştırabilir.","category":"产品更新","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55, KubeRay aracılığıyla çoklu ana bilgisayar dilimlemeyi otomatik olarak düzenleyerek Google Cloud TPU'yu resmi olarak destekliyor - Aioga AI Haberleri","description":"Ray 2.55, Google Cloud TPU için ilk kez birinci sınıf destek sunuyor; geliştiriciler, Ray görevleri ve Actor API aracılığıyla TPU üzerinde dağıtılmış Python yüklerini çalıştırabili...","url":"https://www.aioga.com/tr/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:25:59.017Z"},"vi":{"title":"Ray 2.55 chính thức hỗ trợ Google Cloud TPU, thông qua KubeRay tự động điều phối phân mảnh nhiều máy chủ","summary":"Ray 2.55 lần đầu tiên cung cấp hỗ trợ hạng nhất cho Google Cloud TPU, các nhà phát triển có thể chạy khối lượng công việc Python phân tán trên TPU thông qua API tác vụ và Actor của Ray.","category":"产品更新","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55 chính thức hỗ trợ Google Cloud TPU, thông qua KubeRay tự động điều phối phân mảnh nhiều máy chủ - Tin tức AI Aioga","description":"Ray 2.55 lần đầu tiên cung cấp hỗ trợ hạng nhất cho Google Cloud TPU, các nhà phát triển có thể chạy khối lượng công việc Python phân tán trên TPU thông qua API tác vụ và Actor của...","url":"https://www.aioga.com/vi/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:25:59.778Z"},"id":{"title":"Ray 2.55 secara resmi mendukung Google Cloud TPU, melalui KubeRay secara otomatis mengatur pemotongan multi-host","summary":"Ray 2.55 untuk pertama kali menyediakan dukungan tingkat pertama untuk Google Cloud TPU, memungkinkan pengembang menjalankan beban Python terdistribusi di TPU melalui API tugas dan Aktor Ray.","category":"产品更新","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55 secara resmi mendukung Google Cloud TPU, melalui KubeRay secara otomatis mengatur pemotongan multi-host - Berita AI Aioga","description":"Ray 2.55 untuk pertama kali menyediakan dukungan tingkat pertama untuk Google Cloud TPU, memungkinkan pengembang menjalankan beban Python terdistribusi di TPU melalui API tugas dan...","url":"https://www.aioga.com/id/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:26:36.772Z"},"th":{"title":"Ray 2.55 รองรับอย่างเป็นทางการกับ Google Cloud TPU และจัดการการแบ่งโฮสต์หลายเครื่องโดยอัตโนมัติผ่าน KubeRay","summary":"Ray 2.55 ให้การสนับสนุน Google Cloud TPU ระดับหนึ่งเป็นครั้งแรก ทำให้นักพัฒนาสามารถรันงาน Python แบบกระจายบน TPU ผ่าน Ray Task และ Actor API ได้","category":"产品更新","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55 รองรับอย่างเป็นทางการกับ Google Cloud TPU และจัดการการแบ่งโฮสต์หลายเครื่องโดยอัตโนมัติผ่าน KubeRay - ข่าว AI Aioga","description":"Ray 2.55 ให้การสนับสนุน Google Cloud TPU ระดับหนึ่งเป็นครั้งแรก ทำให้นักพัฒนาสามารถรันงาน Python แบบกระจายบน TPU ผ่าน Ray Task และ Actor API ได้","url":"https://www.aioga.com/th/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:26:46.316Z"},"pl":{"title":"Ray 2.55 oficjalnie wspiera Google Cloud TPU, automatycznie orkiestrując shardy na wielu hostach za pomocą KubeRay","summary":"Ray 2.55 po raz pierwszy oferuje pierwszorzędne wsparcie dla Google Cloud TPU, umożliwiając deweloperom uruchamianie rozproszonych zadań Pythona na TPU za pośrednictwem API zadań i aktorów Ray.","category":"产品更新","source":"Google Developers Blog（RSS）","aggregationSource":"Google Developers Blog（RSS）","pageTitle":"Ray 2.55 oficjalnie wspiera Google Cloud TPU, automatycznie orkiestrując shardy na wielu hostach za pomocą KubeRay - Aioga Wiadomości AI","description":"Ray 2.55 po raz pierwszy oferuje pierwszorzędne wsparcie dla Google Cloud TPU, umożliwiając deweloperom uruchamianie rozproszonych zadań Pythona na TPU za pośrednictwem API zadań i...","url":"https://www.aioga.com/pl/news/cmrth189u36hobitl8fiuyu4z/","contentTranslated":true,"sourceHash":"39e640903d211c0a","translatedAt":"2026-07-23T01:27:31.882Z"}}}}