For uninterrupted computing services
This guide details how to deploy the open‑source Qwen 3.5‑397B‑A17B multimodal LLM on Alibaba Cloud ACK using the RoleBasedGroup (RBG) engine, covering model preparation, Kubernetes resources, role‑based orchestration, performance tuning, and benchmark testing.
This article explains how Kubernetes VolumePopulator can automatically transfer AI training data from low‑cost OSS storage to high‑performance CPFS volumes, enabling on‑demand model loading, cost‑effective hot‑cold data management, and fully automated lifecycle handling in cloud‑native AI workloads.
This article explains how GlobalElasticQuotaTree extends Kubernetes native elastic quota to multi‑cluster environments, providing hierarchical quota structures, Min/Max borrowing, cluster‑level control, and workload‑type support to improve resource utilization for AI platforms.
By integrating Alibaba Cloud ACK’s Kubernetes VolumePopulator with Argo Workflows, this guide shows how to pre‑populate independent high‑performance volumes for each parallel task, eliminating I/O contention, ensuring data isolation, and enabling scalable, serverless‑accelerated pipelines for large‑scale data processing.
This guide walks through preparing the Kimi 2.5 model, uploading it to OSS, configuring persistent storage, and using SGLang, RoleBasedGroup, and Openclaw to deploy a production‑grade inference service on Alibaba Cloud Kubernetes with step‑by‑step commands and YAML examples.
Kimi built a high‑performance, low‑cost AI Agent infrastructure by combining Alibaba Cloud ACK node pools and the ACS Agent Sandbox, addressing challenges of instant sandbox response, state continuity, massive concurrency, cost efficiency, security isolation, and search‑memory integration for production‑grade agents.
This article details how to deploy the 235‑billion‑parameter Qwen3‑235B model using PD‑separation and MoE techniques, explains the associated challenges, and demonstrates a production‑grade solution built on the high‑performance SGLang inference engine and the RoleBasedGroup (RBG) orchestration framework, complete with benchmark results and best‑practice YAML examples.
This guide explains how to set up Alibaba Cloud Service Mesh (ASM) on an ACK Kubernetes cluster, covering prerequisites, two methods of cluster registration, creation of north‑south and east‑west gateways, traffic routing with HTTPRoute, security policies using PeerAuthentication and AuthorizationPolicy, and observability configuration via Telemetry.
This guide explains how to combine AgentScope with Knative to efficiently develop, build, and deploy AI agents using serverless containers, covering key features, pain‑point solutions, installation steps, code examples, deployment commands, and post‑deployment observations.
The article explains how OpenKruise Agents, an open‑source project from Alibaba Cloud, provides a cloud‑native sandbox infrastructure for AI agents on Kubernetes, detailing its architecture, lifecycle management, security challenges, resource pooling, and future roadmap for AI‑driven workloads.
