chore: release 0.4.22

[github-actions]

🚀 Release ${version}

0.4.22 (2026-03-04)

Features

• add --jinja flag for tool/function calling support (#162) (47624ca)
• add 32B models to catalog with --context flag (#88) (6c06602)
• add air-gapped deployment support for local model paths (#85) (31fe8d0)
• Add benchmark command and reorganize documentation (58307be)
• Add benchmark command and reorganize documentation (ac8888e), closes #6
• add custom CA support and fix deprecated image tags (#124) (5ec912e)
• add GPU contention visibility, queue position, and priority classes (#81) (c0220e5)
• add GPU observability config and Grafana dashboard (#105) (571643f)
• Add Helm chart for easy installation (5718804)
• Add Helm chart for easy installation with comprehensive CI testing (3ea3bfd), closes #9
• add license compliance scanning for GGUF models (#188) (c26400a)
• Add Metal GPU support for macOS (Apple Silicon) (f673c26), closes #33
• Add model catalog with 10 pre-configured models (404d722)
• Add model catalog with 10 pre-configured models (Phase 1) (0fd969a)
• Add persistent model cache to avoid re-downloading (83f844f), closes #52
• add Prometheus metrics, OpenTelemetry tracing, and inference observability (#189) (c653ff1)
• add PVC inspection to cache list for orphaned entry detection (#183) (2723d92)
• Add Release Please automation and version-agnostic docs (dc2d54e)
• agent: add --host-ip flag for remote K8s cluster support (#155) (b425569)
• agent: add structured zap logging to metal agent (#164) (e9d143c)
• cli: add comprehensive benchmark test suites and sweeps (#107) (323a28a)
• cli: add stress testing mode to benchmark command (#104) (530c82e)
• controller: make init container image configurable (#128) (38ccdf0)
• deps: upgrade to Kubernetes 1.35 and controller-runtime v0.23.1 (#175) (3c323f4)
• expose llama.cpp parallel slots in InferenceService CRD (#133) (cae7b52)
• gguf: add native Go GGUF parser with CRD integration and CLI inspect (#140) (9d96ed4)
• helm: Add image digest support for production deployments (a38801d)
• helm: add optional NetworkPolicy for controller manager (#135) (8d61ce3)
• Implement automatic port forwarding for benchmark command (472b3ae)
• inference: add flashAttention and contextSize to sample manifest (914c929), closes #145
• Multi-GPU support with layer-based sharding (#47) (4797609)
• Persistent model cache with per-namespace PVC support (ab04261)
• Set up Helm repository on GitHub Pages (8d62737)
• Support configurable context size for llama.cpp server (#73) (6f8e04b)
• Support per-namespace model cache PVCs (c3cb891)
• update model catalog with DeepSeek R1 and refresh stale entries (#131) (89eb5a6)

Bug Fixes

• Add cacheKey to CRD and restrict cache to llmkube-system namespace (464c23d)
• Add CRD keep policy and improve security test reliability (ff32296)
• Add Helm chart publishing to release workflow (8baf9c4)
• Add Helm chart publishing to release workflow (03bab72)
• Add Homebrew archive IDs and v0.3.0 release notes (cea933b)
• Address lint issues in benchmark command (bf80610)
• Address linter errors in catalog implementation (8932e4f)
• Address linter issues in Metal agent code (3f1f678)
• agent: filter InferenceServices by Metal accelerator type (#157) (5737bb7)
• agent: read contextSize from InferenceService CRD (#160) (17f58d4)
• agent: unregister service endpoints on metal process delete (#168) (147b9bc)
• ci: use go-version-file in release workflows (3b14fc8)
• Clean up release process - single release with proper notes (#66) (4deae85)
• cli: use numeric comparison for version checking (#109) (05e0025)
• controller: Add Model watch to InferenceService controller (cb4e201)
• controller: use fully qualified image names for curl (#121) (213660b)
• Correct CLI binary path in E2E tests (41af555)
• correct Metal quickstart docs for selectorless services (#173) (89471ec)
• Don't mark Helm chart release as latest (#70) (761b154)
• enable controller metrics endpoint in Helm chart (#195) (70940af)
• Fix GoReleaser Homebrew tap configuration for v0.3.0 (4e95c04)
• Further increase Helm CI timeout and readiness probe delay (5453d66)
• Further increase Helm CI timeout and readiness probe delay (fd577d3)
• Handle resp.Body.Close error in version check (linter) (fb3adf5)
• Increase Helm chart CI timeout from 2m to 5m (7a08b45)
• Increase Helm chart CI timeout from 2m to 5m (ced2210)
• inference: pass value to --flash-attn for newer llama.cpp versions (#148) (25e08d0)
• InferenceService stuck in Pending when Model becomes Ready (4d20aec)
• Metal agent production fixes and testing improvements (8744c7b)
• prevent command injection in init container shell commands (#172) (3aa9cc3)
• prevent model re-download of cached models after helm upgrade (#203) (a8f9a88)
• remove mutable latest tags and pin container images (#174) (3c4569a)
• Resolve Helm chart CI test failures (9919696)
• Resolve staticcheck SA5011 lint errors and update CONTRIBUTING.md (#60) (c0b5824)
• Sanitize Service names for DNS-1035 compliance (v0.3.3) (db81990)
• Sanitize Service names to comply with DNS-1035 requirements (b431986)
• Set empty component to prevent llmkube- prefix in releases (#68) (45b61c6)
• Skip containerized Deployment for Metal accelerator and add version check (d300e64)
• Skip containerized Deployment for Metal accelerator and add version check (8dab955)
• Suppress Endpoints API deprecation warnings (e70a4b3)
• Trigger GoReleaser and Helm release from Release Please workflow (#64) (9a37a77)
• Update operator deployment to use correct container image (00fee75)
• Update operator deployment to use correct container image (4c67a78)
• Update version.go to 0.2.1 and add automation for future releases (8dd613d)
• Update version.go to 0.2.1 and add automation for future releases (2ff68bd)
• use Recreate strategy for GPU workloads to prevent rolling update deadlock (#196) (2e45181)
• Use simple v* tag format for releases (#62) (bda9f19)
• Use workspace path for kubeconform validation (fc066d8)

Documentation

• add Apple Silicon Metal option to bug report template (#169) (e7689d8)
• Add CLI option to quick start, keep kubectl as fallback (f6829ee)
• add community standards and security policy (#92) (e7c9cad)
• add getting started video to README (#76) (ceb83d7)
• Add Metal Agent (Apple Silicon) support to README (#151) (3579426)
• Add release notes for v0.3.2 (177abf8)
• Add release notes for v0.3.2 (ca1bb12)
• Add release notes for v0.4.0 (144b960)
• Add release notes for v0.4.0 (a61321f)
• Overhaul README and roadmap for public launch (b42c17e)
• rewrite README for clarity, positioning, and growth (#190) (a7fc152)
• Update binary download links to version 0.2.1 (fad530a)
• Update binary download links to version 0.2.1 (63bb0fa)
• update documentation for v0.4.9 GPU scheduling features (#83) (0934e8f)
• Update Helm installation to use GitHub Pages repository (477e037)
• Update MODEL-CACHE.md for per-namespace PVC pattern (0be3f46)
• update README and Metal Agent guide for remote K8s architecture (#156) (79145b2)

---

This PR was generated with Release Please. See documentation.

[Defilan]

Closing stale release-please PR. v0.5.0 was already released. Release-please will create a fresh PR on the next qualifying commit.