Docs/CI: Enable Fake Finish for Docs Only PR (#3350)

.github/workflows/pr-test.yml

@@ -6,11 +6,13 @@ on:
     paths:
       - "python/sglang/**"
       - "test/**"
+      - "docs/**"
   pull_request:
     branches: [ main ]
     paths:
       - "python/sglang/**"
       - "test/**"
+      - "docs/**"
   workflow_dispatch:
     inputs:
       version:
@@ -27,9 +29,38 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
+  filter:
+    runs-on: ubuntu-latest
+    outputs:
+      run_tests: ${{ steps.set_run_tests.outputs.run_tests }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+      - name: Filter changes
+        id: filter
+        uses: dorny/paths-filter@v2
+        with:
+          filters: |
+            docs:
+              - 'docs/**'
+            sglang:
+              - 'python/sglang/**'
+            test:
+              - 'test/**'
+      - name: Set run_tests output
+        id: set_run_tests
+        run: |
+          if [ "${{ steps.filter.outputs.sglang }}" == "true" ] || [ "${{ steps.filter.outputs.test }}" == "true" ]; then
+            echo "run_tests=true" >> $GITHUB_OUTPUT
+          else
+            echo "run_tests=false" >> $GITHUB_OUTPUT
+          fi
 
   unit-test-frontend:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && github.event.pull_request.draft == false
+    needs: filter
+    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
+        github.event.pull_request.draft == false &&
+        needs.filter.outputs.run_tests == 'true'
     runs-on: 1-gpu-runner
     steps:
       - name: Checkout code
@@ -48,7 +79,10 @@ jobs:
           python3 run_suite.py --suite per-commit
 
   unit-test-backend-1-gpu:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && github.event.pull_request.draft == false
+    needs: filter
+    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
+        github.event.pull_request.draft == false &&
+        needs.filter.outputs.run_tests == 'true'
     runs-on: 1-gpu-runner
     strategy:
       fail-fast: false
@@ -70,13 +104,14 @@ jobs:
           RANGE=${{ matrix.range }}
           range_begin=${RANGE%-*}
           range_end=${RANGE#*-}
-
           cd test/srt
           python3 run_suite.py --suite per-commit --range-begin ${range_begin} --range-end ${range_end}
 
-
   unit-test-backend-2-gpu:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && github.event.pull_request.draft == false
+    needs: filter
+    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
+        github.event.pull_request.draft == false &&
+        needs.filter.outputs.run_tests == 'true'
     runs-on: 2-gpu-runner
     steps:
       - name: Checkout code
@@ -113,7 +148,10 @@ jobs:
           python3 test_moe_ep.py
 
   performance-test-1-gpu-part-1:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && github.event.pull_request.draft == false
+    needs: filter
+    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
+        github.event.pull_request.draft == false &&
+        needs.filter.outputs.run_tests == 'true'
     runs-on: 1-gpu-runner
     steps:
       - name: Checkout code
@@ -155,9 +193,11 @@ jobs:
           cd test/srt
           python3 -m unittest test_bench_serving.TestBenchServing.test_online_latency_eagle
 
-
   performance-test-1-gpu-part-2:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && github.event.pull_request.draft == false
+    needs: filter
+    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
+        github.event.pull_request.draft == false &&
+        needs.filter.outputs.run_tests == 'true'
     runs-on: 1-gpu-runner
     steps:
       - name: Checkout code
@@ -188,7 +228,10 @@ jobs:
           python3 -m unittest test_bench_serving.TestBenchServing.test_offline_throughput_default_fp8
 
   performance-test-2-gpu:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && github.event.pull_request.draft == false
+    needs: filter
+    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
+        github.event.pull_request.draft == false &&
+        needs.filter.outputs.run_tests == 'true'
     runs-on: 2-gpu-runner
     steps:
       - name: Checkout code
@@ -224,9 +267,11 @@ jobs:
           cd test/srt
           python3 -m unittest test_bench_serving.TestBenchServing.test_moe_offline_throughput_without_radix_cache
 
-
   accuracy-test-1-gpu:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && github.event.pull_request.draft == false
+    needs: filter
+    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
+        github.event.pull_request.draft == false &&
+        needs.filter.outputs.run_tests == 'true'
     runs-on: 1-gpu-runner
     steps:
       - name: Checkout code
@@ -237,7 +282,6 @@ jobs:
           FLASHINFER_REPO: ${{ inputs.version == 'nightly' && 'https://flashinfer.ai/whl/nightly/cu124/torch2.5/flashinfer' || 'https://flashinfer.ai/whl/cu124/torch2.5/flashinfer' }}
         run: |
           bash scripts/ci_install_dependency.sh
-
           git clone https://github.com/merrymercy/human-eval.git
           cd human-eval
           pip install -e .
@@ -248,9 +292,11 @@ jobs:
           cd test/srt
           python3 test_eval_accuracy_large.py
 
-
   accuracy-test-2-gpu:
-    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') && github.event.pull_request.draft == false
+    needs: filter
+    if: (github.repository == 'sgl-project/sglang' || github.event_name == 'pull_request') &&
+        github.event.pull_request.draft == false &&
+        needs.filter.outputs.run_tests == 'true'
     runs-on: 2-gpu-runner
     steps:
       - name: Checkout code
@@ -261,7 +307,6 @@ jobs:
           FLASHINFER_REPO: ${{ inputs.version == 'nightly' && 'https://flashinfer.ai/whl/nightly/cu124/torch2.5/flashinfer' || 'https://flashinfer.ai/whl/cu124/torch2.5/flashinfer' }}
         run: |
           bash scripts/ci_install_dependency.sh
-
           git clone https://github.com/merrymercy/human-eval.git
           cd human-eval
           pip install -e .
@@ -272,8 +317,8 @@ jobs:
           cd test/srt
           python3 test_moe_eval_accuracy_large.py
 
-
   finish:
+    if: always()
     needs: [
       unit-test-frontend, unit-test-backend-1-gpu, unit-test-backend-2-gpu,
       performance-test-1-gpu-part-1, performance-test-1-gpu-part-2, performance-test-2-gpu,