Container Service simplifies establishment of container management clusters and integrates Alibaba Cloud virtualization, storage, network, and security capabilities to create the optimal container running environment on the cloud.
FollowThis article describes how to use the ACK Gateway with AI Extension plug-in to provide production-level load balancing and intelligent routing capabilities for QwQ-32B models deployed in ACK clusters.
This article focuses on the canary release of models after the large model inference service is deployed in the cloud and the practices of model canary release based on ACK Gateway with AI Extension.
The article introduces how Yahaha migrated its UE5 game STRIDEN to a cloud-native architecture powered by OpenKruiseGame.
The Cloud Native Computing Foundation (CNCF) Technical Oversight Committee (TOC) has voted to accept OpenYurt as an incubating project.
This article presents ACK One's multi-cluster AI job scheduling solution that optimizes resource utilization by distributing Spark jobs across multipl...
This blog briefly introduces Ray and KubeRay, along with the related efforts to support Ray on ACK.
This article describes the observability principles and best practices of GPU-accelerated edge nodes connected to ACK Edge.
This article describes how to use ACK Edge and virtual nodes to meet the elasticity requirements of DeepSeek deployment.
This article describes how to deploy a DeepSeek-R1 inference service in Knative.
This article introduces the practice of using service mesh to deal with service-level disaster recovery.
This article describes how to use Alibaba Cloud Service Mesh (ASM) and Alibaba Cloud Container Service for Kubernetes (ACK) to address zone-level disaster recovery.
This article introduces how to achieve automatic detection of region-level faults and traffic redirection based on ASM.
The hybrid cloud LLM elastic inference solution based on ACK Edge dynamically adjusts GPU resource use between the on-premises data center and the cloud to meet tidal inference traffic demands.
With the help of ACK One registered clusters, we can make full use of ACS GPU computing power of Alibaba Cloud to efficiently deploy the DeepSeek inference model.
This article describes how to use the enhanced capabilities provided by Alibaba Cloud Service Mesh (ASM) to flexibly and comprehensively observe LLM traffic in a cluster.
This article describes an automatic scaling solution for LLM inference services based on Knative.
This article describes the various extension capabilities provided by the ASM data plane proxy, making it easier for you to choose the most suitable extension method to meet your business needs.
This article describes the upgraded container monitoring system of ACK, including the display and overview of major dashboard interfaces.
This article describes how to use the multi-cluster gateway ACK One to implement zone-disaster recovery of public cloud applications.
The key features of OpenYurt v1.6 include node-level traffic multiplexing and enhanced edge autonomy.
Following (0)
See All