kubeai 0.20.0

What's Changed

• bump helm chart versions by @samos123 in #477
• update vLLM GH200 image to 0.8.2 by @samos123 in #480
• fix: use correct accessKeyID values in if statement by @ffais in #478
• Load models and LoRA Adapters from S3 Compatible Storage Server by @ffais in #482
• fix: adds support for custom metrics apiVersion in kubeai helm chart by @grumpydude in #487
• Bump github.com/golang-jwt/jwt/v5 from 5.2.1 to 5.2.2 by @dependabot in #467
• fix flaky s3 test by @samos123 in #492
• fix flaky s3 test take 2 by @samos123 in #493
• add deepseek 70b on gh200 by @samos123 in #494
• feat: Allow Ollama insecure pull using ?insecure=true in url by @samos123 in #491
• feat: Llama 4 support and vLLM 0.8.3 by @samos123 in #495
• support use of JSONPatch for model server pods by @alam0rt in #497
• allow s3 model urls without cache profile by @liebman in #504
• Support envFrom in model spec by @ffais in #489

New Contributors

• @grumpydude made their first contribution in #487
• @alam0rt made their first contribution in #497
• @liebman made their first contribution in #504

Full Changelog: v0.19.0...v0.20.0