chore: rename Go module path + references to match repo slug llm-serving-pack

Makefile

@@ -1,4 +1,4 @@
-# nebari-llm-serving-pack
+# llm-serving-pack
 #
 # Tasks for the Astro/Starlight documentation site (lives in docs/).
 # Run `make help` to list targets.

README.md

@@ -1,4 +1,4 @@
-# nebari-llm-serving-pack
+# llm-serving-pack
 
 A [Nebari](https://github.com/nebari-dev/nebari-infrastructure-core) software pack for serving LLMs. Deploys a Kubernetes operator that manages LLM model serving via [llm-d](https://llm-d.ai), with per-model access control, API key management, and Envoy AI Gateway integration for token counting and rate limiting.
 
@@ -19,8 +19,8 @@ Models can be loaded from HuggingFace (default) or mounted as OCI/modelcar image
 - Kubernetes 1.28+ cluster with [Nebari Infrastructure Core](https://github.com/nebari-dev/nebari-infrastructure-core) deployed
 - [nebari-operator](https://github.com/nebari-dev/nebari-operator) running
 - NVIDIA GPU Operator installed (auto-discovers GPU nodes and manages the device plugin). **Note**: nebari-infrastructure-core does not install this automatically yet - tracked in [nebari-dev/nebari-infrastructure-core#232](https://github.com/nebari-dev/nebari-infrastructure-core/issues/232). Until that is done, install it manually as an ArgoCD app (see [examples/nvidia-gpu-operator.yaml](examples/nvidia-gpu-operator.yaml)).
-- **Envoy Gateway installed and configured for AI Gateway integration** - `extensionApis.enableBackend`, `extensionManager` pointing at the AI Gateway controller service, and `backendResources` allowing `inference.networking.k8s.io/InferencePool`. This is a **hard requirement**; without it, the routing layer 404s at runtime. Ready-to-apply example in [`examples/envoy-gateway.yaml`](examples/envoy-gateway.yaml); see the [Installation guide](https://nebari-dev.github.io/nebari-llm-serving-pack/installation/#6-reconfigure-envoy-gateway-with-ai-gateway-extension-wiring) for details.
-- Envoy AI Gateway installed (v0.5.0+). **Note**: the `envoyAIGateway.install` flag in this chart is not yet implemented - tracked in [#44](https://github.com/nebari-dev/nebari-llm-serving-pack/issues/44). Until that is done, install it manually as an ArgoCD app (see [examples/envoy-ai-gateway.yaml](examples/envoy-ai-gateway.yaml)).
+- **Envoy Gateway installed and configured for AI Gateway integration** - `extensionApis.enableBackend`, `extensionManager` pointing at the AI Gateway controller service, and `backendResources` allowing `inference.networking.k8s.io/InferencePool`. This is a **hard requirement**; without it, the routing layer 404s at runtime. Ready-to-apply example in [`examples/envoy-gateway.yaml`](examples/envoy-gateway.yaml); see the [Installation guide](https://nebari-dev.github.io/llm-serving-pack/installation/#6-reconfigure-envoy-gateway-with-ai-gateway-extension-wiring) for details.
+- Envoy AI Gateway installed (v0.5.0+). **Note**: the `envoyAIGateway.install` flag in this chart is not yet implemented - tracked in [#44](https://github.com/nebari-dev/llm-serving-pack/issues/44). Until that is done, install it manually as an ArgoCD app (see [examples/envoy-ai-gateway.yaml](examples/envoy-ai-gateway.yaml)).
 - [Gateway API Inference Extension](https://github.com/kubernetes-sigs/gateway-api-inference-extension) (GIE) installed (InferencePool / InferenceModel CRDs).
 - A cert-manager `ClusterIssuer` the operator can use for the shared-hostname Certificate. Default expected name is `letsencrypt-production`; override with `platform.tls.clusterIssuer` in the chart values.
 - DNS for `llm.<baseDomain>` and `llm-internal.<baseDomain>` resolving to the shared Gateway's load balancer (a wildcard CNAME on the base domain is the simplest way). Required for HTTP-01 issuance on the shared Certificate.
@@ -253,7 +253,7 @@ The pack expects the following to be available on the cluster:
 
 ## Development
 
-See the [Local Development guide](https://nebari-dev.github.io/nebari-llm-serving-pack/local-development/) for a full walkthrough of the local dev environment.
+See the [Local Development guide](https://nebari-dev.github.io/llm-serving-pack/local-development/) for a full walkthrough of the local dev environment.
 
 ```bash
 # Create kind cluster with all dependencies
@@ -326,15 +326,15 @@ This pack is at alpha maturity (`v0.1.0-alpha.x`). The following limitations app
 
 - **Single-namespace model:** All LLMModels must be in the operator's own namespace. Per-team isolation requires running separate pack installs (one namespace per team). This is a hard constraint imposed by Envoy Gateway's `apiKeyAuth`, which does not support cross-namespace Secret references.
 - **API keys are not continuously tied to group membership.** Keys are issued based on the user's OIDC groups at creation time. If a user later loses group access, existing keys continue to work. The periodic audit that revokes such keys (default interval: 5 minutes) is **off by default** - it only runs when `keyManager.oidcUserinfoURL` is configured, which ships empty. Without it, keys are never revoked on group change. Even when enabled, this is eventual consistency, not real-time revocation.
-- **JWKS path is Keycloak-specific.** The internal endpoint's JWT SecurityPolicy constructs the JWKS URI as `<issuerURL>/protocol/openid-connect/certs`. Non-Keycloak OIDC providers will not work out of the box. Tracked in [#61](https://github.com/nebari-dev/nebari-llm-serving-pack/issues/61).
+- **JWKS path is Keycloak-specific.** The internal endpoint's JWT SecurityPolicy constructs the JWKS URI as `<issuerURL>/protocol/openid-connect/certs`. Non-Keycloak OIDC providers will not work out of the box. Tracked in [#61](https://github.com/nebari-dev/llm-serving-pack/issues/61).
 - **NVIDIA GPUs only.** AMD and Intel accelerators are not supported in v0.1.
 - **No scale-to-zero.** Idle model pods are not scaled down automatically.
 - **No per-key rate limiting or token quotas.** Rate limiting is applied at the model level via Envoy AI Gateway, not per individual API key.
 - **No API key expiration.** Keys do not expire on a schedule; revocation requires either manual deletion or - only when the audit is enabled via `keyManager.oidcUserinfoURL` - the audit detecting lost group access.
 - **No team-level shared API keys.** Each key is tied to an individual user's identity.
 - **OCI model loading uses init-container copy.** Kubernetes image volumes (alpha/beta) are not used; every pod start copies files from the OCI image to a shared emptyDir. On pods with `storage.type: emptyDir` and `preload: true`, every restart triggers a full re-download.
 - **API key and metadata storage is limited to ~1 MiB per model** (Kubernetes Secret/ConfigMap size limit). This supports several thousand keys per model; it is a known scaling ceiling for v0.1.
-- **`envoyAIGateway.install` flag is not yet implemented.** Envoy AI Gateway must be installed separately. Tracked in [#44](https://github.com/nebari-dev/nebari-llm-serving-pack/issues/44).
+- **`envoyAIGateway.install` flag is not yet implemented.** Envoy AI Gateway must be installed separately. Tracked in [#44](https://github.com/nebari-dev/llm-serving-pack/issues/44).
 - **Per-model subdomains are not yet wired into routing.** The `endpoints.external.subdomain` field is validated but unused. All models share `llm.<baseDomain>`; per-model dispatch is by the `model` field in the request body.
 
 ## License

docs/package.json

@@ -1,5 +1,5 @@
 {
-  "name": "nebari-llm-serving-pack-docs-astro",
+  "name": "llm-serving-pack-docs-astro",
   "type": "module",
   "version": "0.0.1",
   "scripts": {

docs/src/content/docs/local-development.md

@@ -1,7 +1,7 @@
 ---
 title: Local Development
 ---
-This guide walks through setting up a local development environment using [kind](https://kind.sigs.k8s.io/) to test the nebari-llm-serving-pack without a full Nebari deployment.
+This guide walks through setting up a local development environment using [kind](https://kind.sigs.k8s.io/) to test the llm-serving-pack without a full Nebari deployment.
 
 > **Scope of this dev path.** The local `kind` setup exercises the
 > operator, key manager, CRD, webhook, and reconciler logic against a

examples/envoy-ai-gateway.yaml

@@ -18,7 +18,7 @@
 #
 # This manual installation is a workaround until the chart's
 # envoyAIGateway.install flag is implemented:
-#   https://github.com/nebari-dev/nebari-llm-serving-pack/issues/44
+#   https://github.com/nebari-dev/llm-serving-pack/issues/44
 #
 # References:
 #   - https://aigateway.envoyproxy.io/docs/getting-started/installation/

examples/envoy-gateway.yaml

@@ -1,6 +1,6 @@
 # Envoy Gateway ArgoCD Application with AI-Gateway-compatible values.
 #
-# The nebari-llm-serving-pack relies on Envoy AI Gateway's ext_proc
+# The llm-serving-pack relies on Envoy AI Gateway's ext_proc
 # filter to extract the `model` field from OpenAI-style request bodies
 # and dispatch per-model. For that filter to be programmed into
 # Envoy's HCM, Envoy Gateway MUST be installed with:

key-manager/cmd/main.go

@@ -17,12 +17,12 @@ import (
 	"k8s.io/client-go/rest"
 	"sigs.k8s.io/controller-runtime/pkg/client"
 
-	llmv1alpha1 "github.com/nebari-dev/nebari-llm-serving-pack/operator/api/v1alpha1"
+	llmv1alpha1 "github.com/nebari-dev/llm-serving-pack/operator/api/v1alpha1"
 
-	"github.com/nebari-dev/nebari-llm-serving-pack/key-manager/internal/api"
-	"github.com/nebari-dev/nebari-llm-serving-pack/key-manager/internal/audit"
-	"github.com/nebari-dev/nebari-llm-serving-pack/key-manager/internal/models"
-	"github.com/nebari-dev/nebari-llm-serving-pack/key-manager/internal/secrets"
+	"github.com/nebari-dev/llm-serving-pack/key-manager/internal/api"
+	"github.com/nebari-dev/llm-serving-pack/key-manager/internal/audit"
+	"github.com/nebari-dev/llm-serving-pack/key-manager/internal/models"
+	"github.com/nebari-dev/llm-serving-pack/key-manager/internal/secrets"
 )
 
 func main() {

key-manager/go.mod

@@ -1,12 +1,12 @@
-module github.com/nebari-dev/nebari-llm-serving-pack/key-manager
+module github.com/nebari-dev/llm-serving-pack/key-manager
 
 go 1.25.8
 
-replace github.com/nebari-dev/nebari-llm-serving-pack/operator => ../operator
+replace github.com/nebari-dev/llm-serving-pack/operator => ../operator
 
 require (
 	github.com/golang-jwt/jwt/v5 v5.3.1
-	github.com/nebari-dev/nebari-llm-serving-pack/operator v0.0.0
+	github.com/nebari-dev/llm-serving-pack/operator v0.0.0
 	golang.org/x/sync v0.18.0
 	k8s.io/api v0.35.0
 	k8s.io/apimachinery v0.35.0

key-manager/internal/api/handler.go

@@ -6,8 +6,8 @@ import (
 	"log/slog"
 	"net/http"
 
-	"github.com/nebari-dev/nebari-llm-serving-pack/key-manager/internal/models"
-	"github.com/nebari-dev/nebari-llm-serving-pack/key-manager/internal/secrets"
+	"github.com/nebari-dev/llm-serving-pack/key-manager/internal/models"
+	"github.com/nebari-dev/llm-serving-pack/key-manager/internal/secrets"
 )
 
 // ModelLister provides model listing for the handler.

key-manager/internal/api/handler_test.go

@@ -11,8 +11,8 @@ import (
 	"testing"
 	"time"
 
-	"github.com/nebari-dev/nebari-llm-serving-pack/key-manager/internal/models"
-	"github.com/nebari-dev/nebari-llm-serving-pack/key-manager/internal/secrets"
+	"github.com/nebari-dev/llm-serving-pack/key-manager/internal/models"
+	"github.com/nebari-dev/llm-serving-pack/key-manager/internal/secrets"
 )
 
 // discardLogger returns a slog logger that discards all output, for tests.

key-manager/internal/audit/auditor.go

@@ -7,8 +7,8 @@ import (
 	"log/slog"
 	"time"
 
-	"github.com/nebari-dev/nebari-llm-serving-pack/key-manager/internal/models"
-	"github.com/nebari-dev/nebari-llm-serving-pack/key-manager/internal/secrets"
+	"github.com/nebari-dev/llm-serving-pack/key-manager/internal/models"
+	"github.com/nebari-dev/llm-serving-pack/key-manager/internal/secrets"
 )
 
 // UserGroupsLookup returns the current OIDC groups for a username.

key-manager/internal/audit/auditor_test.go

@@ -9,9 +9,9 @@ import (
 	"testing"
 	"time"
 
-	"github.com/nebari-dev/nebari-llm-serving-pack/key-manager/internal/audit"
-	"github.com/nebari-dev/nebari-llm-serving-pack/key-manager/internal/models"
-	"github.com/nebari-dev/nebari-llm-serving-pack/key-manager/internal/secrets"
+	"github.com/nebari-dev/llm-serving-pack/key-manager/internal/audit"
+	"github.com/nebari-dev/llm-serving-pack/key-manager/internal/models"
+	"github.com/nebari-dev/llm-serving-pack/key-manager/internal/secrets"
 )
 
 // mockModelLister is a test double for ModelLister.

key-manager/internal/models/watcher.go

@@ -6,7 +6,7 @@ import (
 
 	"sigs.k8s.io/controller-runtime/pkg/client"
 
-	llmv1alpha1 "github.com/nebari-dev/nebari-llm-serving-pack/operator/api/v1alpha1"
+	llmv1alpha1 "github.com/nebari-dev/llm-serving-pack/operator/api/v1alpha1"
 )
 
 // ModelInfo is a simplified view of an LLMModel or PassthroughModel for

key-manager/internal/models/watcher_test.go

@@ -8,8 +8,8 @@ import (
 	"k8s.io/apimachinery/pkg/runtime"
 	"sigs.k8s.io/controller-runtime/pkg/client/fake"
 
-	"github.com/nebari-dev/nebari-llm-serving-pack/key-manager/internal/models"
-	llmv1alpha1 "github.com/nebari-dev/nebari-llm-serving-pack/operator/api/v1alpha1"
+	"github.com/nebari-dev/llm-serving-pack/key-manager/internal/models"
+	llmv1alpha1 "github.com/nebari-dev/llm-serving-pack/operator/api/v1alpha1"
 )
 
 func boolPtr(b bool) *bool { return &b }

key-manager/internal/secrets/manager_test.go

@@ -14,7 +14,7 @@ import (
 	"k8s.io/apimachinery/pkg/types"
 	"sigs.k8s.io/controller-runtime/pkg/client/fake"
 
-	"github.com/nebari-dev/nebari-llm-serving-pack/key-manager/internal/secrets"
+	"github.com/nebari-dev/llm-serving-pack/key-manager/internal/secrets"
 )
 
 // sanitizedPrefix mirrors the production sanitizeUsernameForKey helper so

operator/PROJECT

@@ -7,7 +7,7 @@ domain: nebari.dev
 layout:
 - go.kubebuilder.io/v4
 projectName: operator
-repo: github.com/nebari-dev/nebari-llm-serving-pack/operator
+repo: github.com/nebari-dev/llm-serving-pack/operator
 resources:
 - api:
     crdVersion: v1
@@ -16,7 +16,7 @@ resources:
   domain: nebari.dev
   group: llm
   kind: LLMModel
-  path: github.com/nebari-dev/nebari-llm-serving-pack/operator/api/v1alpha1
+  path: github.com/nebari-dev/llm-serving-pack/operator/api/v1alpha1
   version: v1alpha1
   webhooks:
     validation: true

operator/cmd/main.go

@@ -35,10 +35,10 @@ import (
 	metricsserver "sigs.k8s.io/controller-runtime/pkg/metrics/server"
 	"sigs.k8s.io/controller-runtime/pkg/webhook"
 
-	llmv1alpha1 "github.com/nebari-dev/nebari-llm-serving-pack/operator/api/v1alpha1"
-	"github.com/nebari-dev/nebari-llm-serving-pack/operator/internal/config"
-	"github.com/nebari-dev/nebari-llm-serving-pack/operator/internal/controller"
-	webhookv1alpha1 "github.com/nebari-dev/nebari-llm-serving-pack/operator/internal/webhook/v1alpha1"
+	llmv1alpha1 "github.com/nebari-dev/llm-serving-pack/operator/api/v1alpha1"
+	"github.com/nebari-dev/llm-serving-pack/operator/internal/config"
+	"github.com/nebari-dev/llm-serving-pack/operator/internal/controller"
+	webhookv1alpha1 "github.com/nebari-dev/llm-serving-pack/operator/internal/webhook/v1alpha1"
 	// +kubebuilder:scaffold:imports
 )
 
@@ -221,7 +221,7 @@ func main() {
 		// Deployment; the webhook uses it to enforce that LLMModels are
 		// created in the operator's namespace so their API-key Secrets land
 		// in the same namespace as the SecurityPolicies that reference them.
-		// See https://github.com/nebari-dev/nebari-llm-serving-pack/issues/59.
+		// See https://github.com/nebari-dev/llm-serving-pack/issues/59.
 		operatorNamespace := os.Getenv("POD_NAMESPACE")
 		if err := webhookv1alpha1.SetupLLMModelWebhookWithManager(mgr, operatorNamespace); err != nil {
 			setupLog.Error(err, "unable to create webhook", "webhook", "LLMModel")

operator/go.mod

@@ -1,4 +1,4 @@
-module github.com/nebari-dev/nebari-llm-serving-pack/operator
+module github.com/nebari-dev/llm-serving-pack/operator
 
 go 1.24.5
 

operator/internal/controller/clustertls_singleton.go

@@ -23,8 +23,8 @@ import (
 	"sigs.k8s.io/controller-runtime/pkg/client"
 	logf "sigs.k8s.io/controller-runtime/pkg/log"
 
-	"github.com/nebari-dev/nebari-llm-serving-pack/operator/internal/config"
-	"github.com/nebari-dev/nebari-llm-serving-pack/operator/internal/controller/reconcilers"
+	"github.com/nebari-dev/llm-serving-pack/operator/internal/config"
+	"github.com/nebari-dev/llm-serving-pack/operator/internal/controller/reconcilers"
 )
 
 // defaultClusterTLSResyncInterval is the background resync cadence for the

operator/internal/controller/clustertls_singleton_test.go

@@ -22,8 +22,8 @@ import (
 	"sigs.k8s.io/controller-runtime/pkg/client"
 	"sigs.k8s.io/controller-runtime/pkg/client/fake"
 
-	"github.com/nebari-dev/nebari-llm-serving-pack/operator/internal/config"
-	"github.com/nebari-dev/nebari-llm-serving-pack/operator/internal/controller/reconcilers"
+	"github.com/nebari-dev/llm-serving-pack/operator/internal/config"
+	"github.com/nebari-dev/llm-serving-pack/operator/internal/controller/reconcilers"
 )
 
 // newFakeClientWithGateway builds a fake client that knows about the

operator/internal/controller/llmmodel_controller.go

@@ -36,9 +36,9 @@ import (
 	"sigs.k8s.io/controller-runtime/pkg/controller/controllerutil"
 	logf "sigs.k8s.io/controller-runtime/pkg/log"
 
-	llmv1alpha1 "github.com/nebari-dev/nebari-llm-serving-pack/operator/api/v1alpha1"
-	"github.com/nebari-dev/nebari-llm-serving-pack/operator/internal/config"
-	"github.com/nebari-dev/nebari-llm-serving-pack/operator/internal/controller/reconcilers"
+	llmv1alpha1 "github.com/nebari-dev/llm-serving-pack/operator/api/v1alpha1"
+	"github.com/nebari-dev/llm-serving-pack/operator/internal/config"
+	"github.com/nebari-dev/llm-serving-pack/operator/internal/controller/reconcilers"
 )
 
 const (

operator/internal/controller/llmmodel_controller_test.go

@@ -32,8 +32,8 @@ import (
 	"sigs.k8s.io/controller-runtime/pkg/client"
 	"sigs.k8s.io/controller-runtime/pkg/reconcile"
 
-	llmv1alpha1 "github.com/nebari-dev/nebari-llm-serving-pack/operator/api/v1alpha1"
-	"github.com/nebari-dev/nebari-llm-serving-pack/operator/internal/config"
+	llmv1alpha1 "github.com/nebari-dev/llm-serving-pack/operator/api/v1alpha1"
+	"github.com/nebari-dev/llm-serving-pack/operator/internal/config"
 )
 
 // testConfig returns a minimal OperatorConfig suitable for envtest.

operator/internal/controller/passthroughmodel_controller.go

@@ -33,9 +33,9 @@ import (
 	"sigs.k8s.io/controller-runtime/pkg/controller/controllerutil"
 	logf "sigs.k8s.io/controller-runtime/pkg/log"
 
-	llmv1alpha1 "github.com/nebari-dev/nebari-llm-serving-pack/operator/api/v1alpha1"
-	"github.com/nebari-dev/nebari-llm-serving-pack/operator/internal/config"
-	"github.com/nebari-dev/nebari-llm-serving-pack/operator/internal/controller/reconcilers"
+	llmv1alpha1 "github.com/nebari-dev/llm-serving-pack/operator/api/v1alpha1"
+	"github.com/nebari-dev/llm-serving-pack/operator/internal/config"
+	"github.com/nebari-dev/llm-serving-pack/operator/internal/controller/reconcilers"
 )
 
 // Condition types reported on PassthroughModel status.

operator/internal/controller/passthroughmodel_controller_test.go

@@ -28,7 +28,7 @@ import (
 	"k8s.io/apimachinery/pkg/types"
 	"sigs.k8s.io/controller-runtime/pkg/reconcile"
 
-	llmv1alpha1 "github.com/nebari-dev/nebari-llm-serving-pack/operator/api/v1alpha1"
+	llmv1alpha1 "github.com/nebari-dev/llm-serving-pack/operator/api/v1alpha1"
 )
 
 // newPassthroughReconciler returns a reconciler wired to the envtest client.