diff --git a/.github/workflows/pr-test.yml b/.github/workflows/pr-test.yml
index d1e160017..f25b27402 100644
--- a/.github/workflows/pr-test.yml
+++ b/.github/workflows/pr-test.yml
@@ -20,6 +20,11 @@ on:
         required: false
         type: string
         default: ""
+      force_continue_on_error:
+        description: "Force continue-on-error (test scheduled CI behavior)"
+        required: false
+        type: boolean
+        default: false
 
 concurrency:
   group: pr-test-${{ github.ref }}
@@ -39,6 +44,7 @@ jobs:
       max_parallel: ${{ steps.set-parallel.outputs.max_parallel }}
       b200_runner: ${{ steps.set-runner.outputs.b200_runner }}
       enable_retry: ${{ steps.set-retry.outputs.enable_retry }}
+      continue_on_error: ${{ steps.set-continue-on-error.outputs.continue_on_error }}
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
@@ -98,19 +104,31 @@ jobs:
           echo "enable_retry=true" >> $GITHUB_OUTPUT
           echo "Retry logic enabled for CI"
 
+      - name: Set continue-on-error for scheduled runs
+        id: set-continue-on-error
+        run: |
+          if [[ "${{ github.event_name }}" == "schedule" || "${{ inputs.force_continue_on_error }}" == "true" ]]; then
+            echo "continue_on_error=true" >> $GITHUB_OUTPUT
+            echo "Scheduled run or force flag detected, enabling continue-on-error to run all tests"
+          else
+            echo "continue_on_error=false" >> $GITHUB_OUTPUT
+            echo "Non-scheduled run, continue-on-error disabled"
+          fi
+
       - name: Show filter results in summary (table)
         run: |
           {
             echo "## Change Detection"
             echo ""
-            echo "| Component       | Changed |"
-            echo "|----------------|---------|"
-            echo "| main_package   | ${{ steps.filter.outputs.main_package || steps.scheduled.outputs.main_package }} |"
-            echo "| sgl_kernel     | ${{ steps.filter.outputs.sgl_kernel || steps.scheduled.outputs.sgl_kernel }} |"
-            echo "| multimodal_gen | ${{ steps.filter.outputs.multimodal_gen || steps.scheduled.outputs.multimodal_gen }} |"
-            echo "| max_parallel   | ${{ steps.set-parallel.outputs.max_parallel }} |"
-            echo "| b200_runner    | ${{ steps.set-runner.outputs.b200_runner }} |"
-            echo "| enable_retry   | ${{ steps.set-retry.outputs.enable_retry }} |"
+            echo "| Component         | Changed |"
+            echo "|-------------------|---------|"
+            echo "| main_package      | ${{ steps.filter.outputs.main_package || steps.scheduled.outputs.main_package }} |"
+            echo "| sgl_kernel        | ${{ steps.filter.outputs.sgl_kernel || steps.scheduled.outputs.sgl_kernel }} |"
+            echo "| multimodal_gen    | ${{ steps.filter.outputs.multimodal_gen || steps.scheduled.outputs.multimodal_gen }} |"
+            echo "| max_parallel      | ${{ steps.set-parallel.outputs.max_parallel }} |"
+            echo "| b200_runner       | ${{ steps.set-runner.outputs.b200_runner }} |"
+            echo "| enable_retry      | ${{ steps.set-retry.outputs.enable_retry }} |"
+            echo "| continue_on_error | ${{ steps.set-continue-on-error.outputs.continue_on_error }} |"
           } >> $GITHUB_STEP_SUMMARY
 
   # =============================================== PR Gate ====================================================
@@ -411,9 +429,13 @@ jobs:
         timeout-minutes: 10
         run: |
           cd test/
-          python3 run_suite.py --hw cuda --suite stage-a-test-1
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
+          python3 run_suite.py --hw cuda --suite stage-a-test-1 $CONTINUE_ON_ERROR_FLAG
           # temporarily put backend-independent cpu tests here
-          python3 run_suite.py --hw cpu --suite default
+          python3 run_suite.py --hw cpu --suite default $CONTINUE_ON_ERROR_FLAG
 
   stage-b-test-small-1-gpu:
     needs: [check-changes, call-gate, stage-a-test-1, sgl-kernel-build-wheels]
@@ -454,7 +476,11 @@ jobs:
         timeout-minutes: 30
         run: |
           cd test/
-          python3 run_suite.py --hw cuda --suite stage-b-test-small-1-gpu --auto-partition-id ${{ matrix.partition }} --auto-partition-size 4
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
+          python3 run_suite.py --hw cuda --suite stage-b-test-small-1-gpu --auto-partition-id ${{ matrix.partition }} --auto-partition-size 4 $CONTINUE_ON_ERROR_FLAG
 
   stage-b-test-large-1-gpu:
     needs: [check-changes, call-gate, stage-a-test-1, sgl-kernel-build-wheels]
@@ -491,7 +517,11 @@ jobs:
         timeout-minutes: 30
         run: |
           cd test/
-          python3 run_suite.py --hw cuda --suite stage-b-test-large-1-gpu
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
+          python3 run_suite.py --hw cuda --suite stage-b-test-large-1-gpu $CONTINUE_ON_ERROR_FLAG
 
   stage-b-test-large-2-gpu:
     needs: [check-changes, call-gate, stage-a-test-1, sgl-kernel-build-wheels]
@@ -528,7 +558,11 @@ jobs:
         timeout-minutes: 30
         run: |
           cd test/
-          python3 run_suite.py --hw cuda --suite stage-b-test-large-2-gpu
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
+          python3 run_suite.py --hw cuda --suite stage-b-test-large-2-gpu $CONTINUE_ON_ERROR_FLAG
 
   stage-c-test-large-4-gpu:
     needs: [check-changes, call-gate, stage-b-test-small-1-gpu, stage-b-test-large-1-gpu, stage-b-test-large-2-gpu, sgl-kernel-build-wheels]
@@ -565,7 +599,11 @@ jobs:
         timeout-minutes: 30
         run: |
           cd test/
-          python3 run_suite.py --hw cuda --suite stage-c-test-large-4-gpu
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
+          python3 run_suite.py --hw cuda --suite stage-c-test-large-4-gpu $CONTINUE_ON_ERROR_FLAG
 
   multimodal-gen-test-1-gpu:
     needs: [check-changes, call-gate, sgl-kernel-build-wheels]
@@ -603,10 +641,15 @@ jobs:
         timeout-minutes: 60
         run: |
           cd python
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
           python3 sglang/multimodal_gen/test/run_suite.py \
             --suite 1-gpu \
             --partition-id ${{ matrix.part }} \
-            --total-partitions 2
+            --total-partitions 2 \
+            $CONTINUE_ON_ERROR_FLAG
 
 
   multimodal-gen-test-2-gpu:
@@ -646,10 +689,15 @@ jobs:
         timeout-minutes: 60
         run: |
           cd python
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
           python3 sglang/multimodal_gen/test/run_suite.py \
             --suite 2-gpu \
             --partition-id ${{ matrix.part }} \
-            --total-partitions 2
+            --total-partitions 2 \
+            $CONTINUE_ON_ERROR_FLAG
 
   quantization-test:
       needs: [check-changes, call-gate, stage-a-test-1]
@@ -688,7 +736,11 @@ jobs:
             if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
               RETRY_FLAG="--enable-retry"
             fi
-            python3 run_suite.py --suite quantization_test $RETRY_FLAG
+            CONTINUE_ON_ERROR_FLAG=""
+            if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+              CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+            fi
+            python3 run_suite.py --suite quantization_test $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
 
   unit-test-backend-1-gpu:
     needs: [check-changes, call-gate, stage-a-test-1]
@@ -734,7 +786,11 @@ jobs:
           if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
             RETRY_FLAG="--enable-retry"
           fi
-          python3 run_suite.py --suite per-commit-1-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 13 $RETRY_FLAG
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
+          python3 run_suite.py --suite per-commit-1-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 13 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
 
 
   stage-b-test-4-gpu-b200:
@@ -775,7 +831,11 @@ jobs:
         timeout-minutes: 30
         run: |
           cd test
-          IS_BLACKWELL=1 python3 run_suite.py --hw cuda --suite stage-b-test-4-gpu-b200
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
+          IS_BLACKWELL=1 python3 run_suite.py --hw cuda --suite stage-b-test-4-gpu-b200 $CONTINUE_ON_ERROR_FLAG
 
 
   unit-test-backend-2-gpu:
@@ -821,7 +881,11 @@ jobs:
           if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
             RETRY_FLAG="--enable-retry"
           fi
-          python3 run_suite.py --suite per-commit-2-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 $RETRY_FLAG
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
+          python3 run_suite.py --suite per-commit-2-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
 
   unit-test-backend-4-gpu:
     needs: [check-changes, call-gate, unit-test-backend-2-gpu, stage-b-test-4-gpu-b200]
@@ -866,7 +930,11 @@ jobs:
           if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
             RETRY_FLAG="--enable-retry"
           fi
-          python3 run_suite.py --suite per-commit-4-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 $RETRY_FLAG
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
+          python3 run_suite.py --suite per-commit-4-gpu --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
 
   unit-test-backend-8-gpu-h200:
     needs: [check-changes, call-gate, unit-test-backend-2-gpu, stage-b-test-4-gpu-b200]
@@ -917,7 +985,11 @@ jobs:
           if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
             RETRY_FLAG="--enable-retry"
           fi
-          python3 run_suite.py --suite per-commit-8-gpu-h200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 $RETRY_FLAG
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
+          python3 run_suite.py --suite per-commit-8-gpu-h200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
 
   unit-test-backend-8-gpu-h20:
     needs: [check-changes, call-gate, unit-test-backend-2-gpu, stage-b-test-4-gpu-b200]
@@ -963,7 +1035,11 @@ jobs:
           if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
             RETRY_FLAG="--enable-retry"
           fi
-          python3 run_suite.py --suite per-commit-8-gpu-h20 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 $RETRY_FLAG
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
+          python3 run_suite.py --suite per-commit-8-gpu-h20 --auto-partition-id ${{ matrix.part }} --auto-partition-size 2 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
 
   performance-test-1-gpu-part-1:
     needs: [check-changes, call-gate, stage-a-test-1]
@@ -1336,7 +1412,11 @@ jobs:
           if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
             RETRY_FLAG="--enable-retry"
           fi
-          python3 run_suite.py --suite per-commit-4-gpu-deepep $RETRY_FLAG
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
+          python3 run_suite.py --suite per-commit-4-gpu-deepep $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
 
   unit-test-deepep-8-gpu:
     needs: [check-changes, call-gate, unit-test-backend-2-gpu, stage-b-test-4-gpu-b200]
@@ -1377,7 +1457,11 @@ jobs:
           if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
             RETRY_FLAG="--enable-retry"
           fi
-          python3 run_suite.py --suite per-commit-8-gpu-h200-deepep $RETRY_FLAG
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
+          python3 run_suite.py --suite per-commit-8-gpu-h200-deepep $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
 
   unit-test-backend-4-gpu-b200:
     needs: [check-changes, call-gate, unit-test-backend-2-gpu, stage-b-test-4-gpu-b200]
@@ -1423,7 +1507,11 @@ jobs:
           if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
             RETRY_FLAG="--enable-retry"
           fi
-          IS_BLACKWELL=1 python3 run_suite.py --suite per-commit-4-gpu-b200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 1800 $RETRY_FLAG
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
+          IS_BLACKWELL=1 python3 run_suite.py --suite per-commit-4-gpu-b200 --auto-partition-id ${{ matrix.part }} --auto-partition-size 3 --timeout-per-file 1800 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
 
   unit-test-backend-4-gpu-gb200:
     needs: [check-changes, call-gate, unit-test-backend-2-gpu, stage-b-test-4-gpu-b200, sgl-kernel-build-wheels-arm]
@@ -1466,7 +1554,11 @@ jobs:
           if [[ "${{ needs.check-changes.outputs.enable_retry }}" == "true" ]]; then
             RETRY_FLAG="--enable-retry"
           fi
-          python3 run_suite.py --suite per-commit-4-gpu-gb200 --auto-partition-id 0 --auto-partition-size 1 --timeout-per-file 3600 $RETRY_FLAG
+          CONTINUE_ON_ERROR_FLAG=""
+          if [[ "${{ needs.check-changes.outputs.continue_on_error }}" == "true" ]]; then
+            CONTINUE_ON_ERROR_FLAG="--continue-on-error"
+          fi
+          python3 run_suite.py --suite per-commit-4-gpu-gb200 --auto-partition-id 0 --auto-partition-size 1 --timeout-per-file 3600 $RETRY_FLAG $CONTINUE_ON_ERROR_FLAG
 
   pr-test-finish:
     needs:
diff --git a/python/sglang/multimodal_gen/test/run_suite.py b/python/sglang/multimodal_gen/test/run_suite.py
index eaa103a6b..35fea064f 100644
--- a/python/sglang/multimodal_gen/test/run_suite.py
+++ b/python/sglang/multimodal_gen/test/run_suite.py
@@ -67,6 +67,12 @@ def parse_args():
         default=None,
         help="Pytest filter expression (passed to pytest -k)",
     )
+    parser.add_argument(
+        "--continue-on-error",
+        action="store_true",
+        default=False,
+        help="Continue running remaining tests even if one fails (for CI consistency; pytest already continues by default)",
+    )
     return parser.parse_args()