# KServe

Published articles for KServe.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Using ArgoCD to Manage AI Model Deployments with GitOps

DevFeed: [Using ArgoCD to Manage AI Model Deployments with GitOps](<https://devfeed.tech/articles/using-argocd-to-manage-ai-model-deployments-with-gitops-17479.md>)

Original publisher: [Read original article](<https://kodekloud.com/blog/argocd-gitops-ai-model-deployments/>)

Author: Pramodh Kumar M

Published: 2026-07-28T18:24:57Z

Content type: tutorial

Language: en

Sources: [Kubernetes - KodeKloud Blog | DevOps, Cloud, Kubernetes, AI Tutorials & More](<https://devfeed.tech/sources/kubernetes-kodekloud-blog-devops-cloud-kubernetes-ai-tutorials-more.md>)

Topics: [GitOps](<https://devfeed.tech/topics/gitops.md>), [argocd](<https://devfeed.tech/topics/argocd.md>), [model-deployment](<https://devfeed.tech/topics/model-deployment.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [model-serving](<https://devfeed.tech/topics/model-serving.md>), [Architecture & Design](<https://devfeed.tech/topics/architecture-design.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [argo-rollouts-model-promotion](<https://devfeed.tech/tags/argo-rollouts-model-promotion.md>), [argocd](<https://devfeed.tech/tags/argocd.md>), [argocd-ai-model-deployment](<https://devfeed.tech/tags/argocd-ai-model-deployment.md>), [argocd-applicationset](<https://devfeed.tech/tags/argocd-applicationset.md>), [argocd-sync-waves](<https://devfeed.tech/tags/argocd-sync-waves.md>), [automation](<https://devfeed.tech/tags/automation.md>), [ci-cd](<https://devfeed.tech/tags/ci-cd.md>), [declarative-model-serving](<https://devfeed.tech/tags/declarative-model-serving.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [devops](<https://devfeed.tech/tags/devops.md>), [gitops](<https://devfeed.tech/tags/gitops.md>), [gitops-for-ai-model-deployments](<https://devfeed.tech/tags/gitops-for-ai-model-deployments.md>), [gitops-mlops](<https://devfeed.tech/tags/gitops-mlops.md>), [kserve](<https://devfeed.tech/tags/kserve.md>), [kserve-canary-deployment](<https://devfeed.tech/tags/kserve-canary-deployment.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [kubernetes-model-deployment-rollback](<https://devfeed.tech/tags/kubernetes-model-deployment-rollback.md>), [ml-model-deployment](<https://devfeed.tech/tags/ml-model-deployment.md>), [ml-model-versioning](<https://devfeed.tech/tags/ml-model-versioning.md>), [mlops](<https://devfeed.tech/tags/mlops.md>), [model-deployment](<https://devfeed.tech/tags/model-deployment.md>), [model-registry-to-git-automation](<https://devfeed.tech/tags/model-registry-to-git-automation.md>), [model-serving](<https://devfeed.tech/tags/model-serving.md>), [pull-requests](<https://devfeed.tech/tags/pull-requests.md>), [standard](<https://devfeed.tech/tags/standard.md>), [tutorial](<https://devfeed.tech/tags/tutorial.md>)

### AI overview

This tutorial explains how to use ArgoCD and GitOps to deploy AI models while accounting for model weights stored outside container images. It covers pinned model references, rollback and recovery, synchronization ordering, readiness probes, evaluation-based promotion gates, and KServe status handling.

### Source excerpt

Your microservices deploy through pull requests with full audit trails. Your models deploy because someone ran a script. Here is how to close that gap with ArgoCD, and what changes when the artifact weighs four gigabytes.

## Protect your AI workloads from supply chain attacks

DevFeed: [Protect your AI workloads from supply chain attacks](<https://devfeed.tech/articles/protect-your-ai-workloads-from-supply-chain-attacks-13205.md>)

Original publisher: [Read original article](<https://www.chainguard.dev/unchained/protect-your-ai-workloads-from-supply-chain-attacks>)

Published: 2026-01-30T00:00:00Z

Content type: article

Language: en

Sources: [Chainguard: Unchained](<https://devfeed.tech/sources/chainguard-unchained.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Containers](<https://devfeed.tech/topics/containers.md>), [chainguard](<https://devfeed.tech/topics/chainguard.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>), [AI Strategy](<https://devfeed.tech/topics/ai-strategy.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>), [Security](<https://devfeed.tech/topics/security.md>), [PyTorch](<https://devfeed.tech/topics/pytorch.md>), [Tensorflow](<https://devfeed.tech/topics/tensorflow.md>), [MLOps](<https://devfeed.tech/topics/mlops.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-containers](<https://devfeed.tech/tags/ai-containers.md>), [chainguard](<https://devfeed.tech/tags/chainguard.md>), [chainguard-containers](<https://devfeed.tech/tags/chainguard-containers.md>), [chainguard-for-ai](<https://devfeed.tech/tags/chainguard-for-ai.md>), [chainguard-libraries](<https://devfeed.tech/tags/chainguard-libraries.md>), [containers](<https://devfeed.tech/tags/containers.md>), [cudnn](<https://devfeed.tech/tags/cudnn.md>), [cves](<https://devfeed.tech/tags/cves.md>), [data-processing](<https://devfeed.tech/tags/data-processing.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [kserve](<https://devfeed.tech/tags/kserve.md>), [legacy](<https://devfeed.tech/tags/legacy.md>), [libraries](<https://devfeed.tech/tags/libraries.md>), [mlops](<https://devfeed.tech/tags/mlops.md>), [nemo](<https://devfeed.tech/tags/nemo.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [python](<https://devfeed.tech/tags/python.md>), [pytorch](<https://devfeed.tech/tags/pytorch.md>), [security](<https://devfeed.tech/tags/security.md>), [security-vulnerabilities](<https://devfeed.tech/tags/security-vulnerabilities.md>), [supply-chain](<https://devfeed.tech/tags/supply-chain.md>), [supply-chain-attacks](<https://devfeed.tech/tags/supply-chain-attacks.md>), [zero-cve-containers](<https://devfeed.tech/tags/zero-cve-containers.md>)

### AI overview

The article discusses security and operational challenges in AI/ML workloads, including complex dependencies, bloated artifacts, infrastructure sprawl, and unremediated CVEs. It presents Chainguard Containers' minimal images for AI workloads as a way to reduce attack surface, storage needs, and deployment overhead, and cites a 50 MB gpu-operator image compared with a 170 MB upstream equivalent.

### Source excerpt

Chainguard secures AI adoption with minimal, zero-CVE containers and source-built libraries that prevent supply chain malware while keeping developers fast.