Merge branch 'main' into fixconn

Author: revit13

.github/workflows/ci-pr-checks.yaml

@@ -363,6 +363,7 @@ jobs:
           E2E_LABEL_FILTER: ${{ matrix.suite.label-filter }}
           PULL_SIDECAR_IMAGE: "false"
           PULL_VLLM_RENDER_IMAGE: "false"
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
         run: make test-e2e-gaie-run
 
   e2e-router:
@@ -450,4 +451,5 @@ jobs:
           E2E_LABEL_FILTER: ${{ matrix.suite.label-filter }}
           LOAD_VLLM_RENDER_IMAGE: ${{ matrix.suite.needs-renderer }}
           PULL_VLLM_RENDER_IMAGE: "false"
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
         run: make test-e2e-router-run

.github/workflows/ci-release.yaml

@@ -51,3 +51,43 @@ jobs:
       tag: ${{ needs.set-params.outputs.tag }}
       prerelease: ${{ fromJSON(needs.set-params.outputs.prerelease) }}
       chart-suffix: ""
+
+  upload-artifacts:
+    needs: set-params
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - name: Checkout source
+        uses: actions/checkout@v6
+
+      - name: Set up Go
+        uses: actions/setup-go@v5
+        with:
+          go-version-file: go.mod
+
+      - name: Setup Kubectl
+        uses: azure/setup-kubectl@v4
+        with:
+          version: 'latest'
+
+      - name: Build Artifacts
+        run: |
+          make artifacts
+
+      - name: Upload Release Assets
+        env:
+          GITHUB_TOKEN: ${{ github.token }}
+        run: |
+          files=$(find artifacts -type f -size +0c | tr '\n' ' ')
+          if [ -z "$files" ]; then
+            echo "No artifacts to upload."
+            exit 0
+          fi
+          if gh release view "${{ needs.set-params.outputs.tag }}" >/dev/null 2>&1; then
+            gh release upload "${{ needs.set-params.outputs.tag }}" $files --clobber
+          else
+            echo "Release ${{ needs.set-params.outputs.tag }} does not exist. Creating a draft release..."
+            gh release create "${{ needs.set-params.outputs.tag }}" $files --draft --title "${{ needs.set-params.outputs.tag }}" --notes "Release ${{ needs.set-params.outputs.tag }}"
+          fi
+

Makefile

@@ -122,7 +122,7 @@ endif
 # Should we pass ALL env vars here?
 E2E_ENV_VARS = EPP_IMAGE VLLM_IMAGE SIDECAR_IMAGE VLLM_RENDER_IMAGE \
                E2E_KEEP_CLUSTER_ON_FAILURE E2E_PORT E2E_METRICS_PORT K8S_CONTEXT READY_TIMEOUT \
-               E2E_LABEL_FILTER LOAD_VLLM_RENDER_IMAGE
+               E2E_LABEL_FILTER LOAD_VLLM_RENDER_IMAGE HF_TOKEN
 BUILDER_E2E_ENV_FLAGS = $(foreach v,$(E2E_ENV_VARS),$(if $($(v)),-e '$(v)=$($(v))'))
 ifneq ($(filter command line environment,$(origin NAMESPACE)),)
 BUILDER_E2E_ENV_FLAGS += -e NAMESPACE=$(NAMESPACE)
@@ -360,6 +360,19 @@ helm-push-standalone: ## Package and push the llm-d-router-standalone Helm chart
 	$(MAKE) helm-push CHART=llm-d-router-standalone
 
 
+##@ Release
+
+.PHONY: artifacts
+artifacts: yq check-kustomize ## Generate release artifacts (CRD manifests)
+	if [ -d artifacts ]; then rm -rf artifacts; fi
+	mkdir -p artifacts
+	kubectl kustomize config/crd > artifacts/manifests_all.yaml
+	$(YQ) -P 'select(.spec.group == "llm-d.ai")' artifacts/manifests_all.yaml > artifacts/manifests.yaml
+	rm -f artifacts/manifests_all.yaml
+	$(YQ) -P 'select(.spec.versions | map(.name == "v1") | any)' artifacts/manifests.yaml > artifacts/v1-manifests.yaml
+	$(YQ) -P 'select(.spec.versions | map(.name != "v1") | all)' artifacts/manifests.yaml > artifacts/experimental-manifests.yaml
+
+
 ##@ Coverage
 
 COVERAGE_DIR       ?= coverage

test/e2e/setup_test.go

@@ -4,6 +4,7 @@ import (
 	"fmt"
 	"io"
 	"net/http"
+	"os"
 	"strconv"
 	"time"
 
@@ -31,7 +32,7 @@ func createModelServersFromKustomize(kustomizeDir string, extra map[string]strin
 		"${DECODE_ROLE}":             "",
 		"${EPP_NAME}":                "e2e-epp",
 		"${NAMESPACE}":               nsName,
-		"${HF_TOKEN}":                "",
+		"${HF_TOKEN}":                os.Getenv("HF_TOKEN"),
 		"${VLLM_EXTRA_ARGS_E}":       "",
 		"${VLLM_EXTRA_ARGS_P}":       "",
 		"${VLLM_EXTRA_ARGS_D}":       "",

test/e2e/utils_test.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"io"
 	"net/http"
+	"os"
 	"os/exec"
 	"strconv"
 	"strings"
@@ -193,9 +194,15 @@ func removeEmptyLabels(inputs []string) []string {
 }
 
 func isModelReal(modelName string) bool {
-	url := "https://huggingface.co/api/models/" + modelName
+	req, err := http.NewRequest("GET", "https://huggingface.co/api/models/"+modelName, nil)
+	if err != nil {
+		return false
+	}
+	if token := os.Getenv("HF_TOKEN"); token != "" {
+		req.Header.Set("Authorization", "Bearer "+token)
+	}
 
-	resp, err := http.Get(url)
+	resp, err := http.DefaultClient.Do(req)
 	if err != nil {
 		return false
 	}