diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
index 21c800f8a..d92488913 100644
--- a/.github/workflows/ci.yml
+++ b/.github/workflows/ci.yml
@@ -1,80 +1,26 @@
-name: Release model-runner images for CE
-run-name: Release model-runner images for CE, version ${{ inputs.releaseTag }}
+name: CI
 
 on:
-  workflow_dispatch:
-    inputs:
-      pushLatest:
-        description: 'Tag images produced by this job as latest'
-        required: false
-        type: boolean
-        default: false
-      releaseTag:
-        description: 'Release tag'
-        required: false
-        type: string
-        default: "test"
+  pull_request:
+    branches: [ main ]
+  push:
+    branches: [ main ]
 
 jobs:
-  build:
+  test:
     runs-on: ubuntu-latest
     steps:
-      - name: Checkout repo
+      - name: Checkout code
         uses: actions/checkout@v4
 
-      - name: Format tags
-        id: tags
-        shell: bash
-        run: |
-          echo "cpu<<EOF" >> "$GITHUB_OUTPUT"
-          echo "docker/model-runner:${{ inputs.releaseTag }}" >> "$GITHUB_OUTPUT"
-          if [ "${{ inputs.pushLatest }}" == "true" ]; then
-            echo "docker/model-runner:latest" >> "$GITHUB_OUTPUT"
-          fi
-          echo 'EOF' >> "$GITHUB_OUTPUT"
-          echo "cuda<<EOF" >> "$GITHUB_OUTPUT"
-          echo "docker/model-runner:${{ inputs.releaseTag }}-cuda" >> "$GITHUB_OUTPUT"
-          if [ "${{ inputs.pushLatest }}" == "true" ]; then
-            echo "docker/model-runner:latest-cuda" >> "$GITHUB_OUTPUT"
-          fi
-          echo 'EOF' >> "$GITHUB_OUTPUT"
-
-      - name: Log in to DockerHub
-        uses: docker/login-action@v3
+      - name: Set up Go
+        uses: actions/setup-go@v5
         with:
-          username: "docker"
-          password: ${{ secrets.ORG_ACCESS_TOKEN }}
+          go-version: 1.24.2
+          cache: true
 
-      - name: Set up Buildx
-        uses: docker/setup-buildx-action@v3
-        with:
-          version: "lab:latest"
-          driver: cloud
-          endpoint: "docker/make-product-smarter"
-          install: true
+      - name: Run tests
+        run: go test -v ./...
 
-      - name: Build CPU image
-        uses: docker/build-push-action@v5
-        with:
-          file: Dockerfile
-          platforms: linux/amd64, linux/arm64
-          build-args: |
-            "LLAMA_SERVER_VERSION=latest"
-          push: true
-          sbom: true
-          provenance: mode=max
-          tags: ${{ steps.tags.outputs.cpu }}
-
-      - name: Build CUDA image
-        uses: docker/build-push-action@v5
-        with:
-          file: Dockerfile
-          platforms: linux/amd64, linux/arm64
-          build-args: |
-            "LLAMA_SERVER_VERSION=latest"
-            "LLAMA_SERVER_VARIANT=cuda"
-            "BASE_IMAGE=nvidia/cuda:12.9.0-cudnn-runtime-ubuntu24.04"
-          push: true
-          sbom: true
-          provenance: mode=max
-          tags: ${{ steps.tags.outputs.cuda }}
+      - name: Run tests with race detection
+        run: go test -race ./...
\ No newline at end of file
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
new file mode 100644
index 000000000..6ca0bc548
--- /dev/null
+++ b/.github/workflows/release.yml
@@ -0,0 +1,96 @@
+name: Release model-runner images for CE
+run-name: Release model-runner images for CE, version ${{ inputs.releaseTag }}
+
+on:
+  workflow_dispatch:
+    inputs:
+      pushLatest:
+        description: 'Tag images produced by this job as latest'
+        required: false
+        type: boolean
+        default: false
+      releaseTag:
+        description: 'Release tag'
+        required: false
+        type: string
+        default: "test"
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Go
+        uses: actions/setup-go@v5
+        with:
+          go-version: 1.24.2
+          cache: true
+
+      - name: Run tests
+        run: go test ./...
+
+  build:
+    needs: test
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@v4
+
+      - name: Format tags
+        id: tags
+        shell: bash
+        run: |
+          echo "cpu<<EOF" >> "$GITHUB_OUTPUT"
+          echo "docker/model-runner:${{ inputs.releaseTag }}" >> "$GITHUB_OUTPUT"
+          if [ "${{ inputs.pushLatest }}" == "true" ]; then
+            echo "docker/model-runner:latest" >> "$GITHUB_OUTPUT"
+          fi
+          echo 'EOF' >> "$GITHUB_OUTPUT"
+          echo "cuda<<EOF" >> "$GITHUB_OUTPUT"
+          echo "docker/model-runner:${{ inputs.releaseTag }}-cuda" >> "$GITHUB_OUTPUT"
+          if [ "${{ inputs.pushLatest }}" == "true" ]; then
+            echo "docker/model-runner:latest-cuda" >> "$GITHUB_OUTPUT"
+          fi
+          echo 'EOF' >> "$GITHUB_OUTPUT"
+
+      - name: Log in to DockerHub
+        uses: docker/login-action@v3
+        with:
+          username: "docker"
+          password: ${{ secrets.ORG_ACCESS_TOKEN }}
+
+      - name: Set up Buildx
+        uses: docker/setup-buildx-action@v3
+        with:
+          version: "lab:latest"
+          driver: cloud
+          endpoint: "docker/make-product-smarter"
+          install: true
+
+      - name: Build CPU image
+        uses: docker/build-push-action@v5
+        with:
+          file: Dockerfile
+          platforms: linux/amd64, linux/arm64
+          build-args: |
+            "LLAMA_SERVER_VERSION=latest"
+          push: true
+          sbom: true
+          provenance: mode=max
+          tags: ${{ steps.tags.outputs.cpu }}
+
+      - name: Build CUDA image
+        uses: docker/build-push-action@v5
+        with:
+          file: Dockerfile
+          platforms: linux/amd64, linux/arm64
+          build-args: |
+            "LLAMA_SERVER_VERSION=latest"
+            "LLAMA_SERVER_VARIANT=cuda"
+            "BASE_IMAGE=nvidia/cuda:12.9.0-cudnn-runtime-ubuntu24.04"
+          push: true
+          sbom: true
+          provenance: mode=max
+          tags: ${{ steps.tags.outputs.cuda }}
diff --git a/pkg/inference/models/manager_test.go b/pkg/inference/models/manager_test.go
index 51759375e..62ae16ba8 100644
--- a/pkg/inference/models/manager_test.go
+++ b/pkg/inference/models/manager_test.go
@@ -2,7 +2,6 @@ package models
 
 import (
 	"context"
-	"github.com/google/go-containerregistry/pkg/registry"
 	"net/http/httptest"
 	"net/url"
 	"os"
@@ -10,6 +9,8 @@ import (
 	"strings"
 	"testing"
 
+	"github.com/google/go-containerregistry/pkg/registry"
+
 	"github.com/docker/model-distribution/builder"
 	reg "github.com/docker/model-distribution/registry"
 
@@ -108,7 +109,7 @@ func TestPullModel(t *testing.T) {
 			m := NewManager(log, ClientConfig{
 				StoreRootPath: tempDir,
 				Logger:        log.WithFields(logrus.Fields{"component": "model-manager"}),
-			})
+			}, nil)
 
 			r := httptest.NewRequest("POST", "/models/create", strings.NewReader(`{"from": "`+tag+`"}`))
 			if tt.acceptHeader != "" {