diff --git a/.github/workflows/cuda.yml b/.github/workflows/cuda.yml
index 48a851338af..71f98c03196 100644
--- a/.github/workflows/cuda.yml
+++ b/.github/workflows/cuda.yml
@@ -159,7 +159,7 @@ jobs:
               repo: "google"
               name: "gemma-3-4b-it"
             quant: "quantized-int4-weight-only"
-          # Voxtral Realtime only supports int4-tile-packed on CUDA (offline mode)
+          # Voxtral Realtime only supports int4-tile-packed on CUDA
           - model:
               repo: "mistralai"
               name: "Voxtral-Mini-4B-Realtime-2602"
@@ -197,12 +197,7 @@ jobs:
           echo "::endgroup::"
         fi
 
-        # Voxtral Realtime uses offline mode for CUDA CI (not streaming)
-        VR_MODE=""
-        if [ "${{ matrix.model.name }}" = "Voxtral-Mini-4B-Realtime-2602" ]; then
-          VR_MODE="vr-offline"
-        fi
-        source .ci/scripts/export_model_artifact.sh cuda "${{ matrix.model.repo }}/${{ matrix.model.name }}" "${{ matrix.quant }}" "${RUNNER_ARTIFACT_DIR}" "$VR_MODE"
+        source .ci/scripts/export_model_artifact.sh cuda "${{ matrix.model.repo }}/${{ matrix.model.name }}" "${{ matrix.quant }}" "${RUNNER_ARTIFACT_DIR}"
 
   test-model-cuda-e2e:
     name: test-model-cuda-e2e
@@ -237,7 +232,7 @@ jobs:
               repo: "google"
               name: "gemma-3-4b-it"
             quant: "quantized-int4-weight-only"
-          # Voxtral Realtime only supports int4-tile-packed on CUDA (offline mode)
+          # Voxtral Realtime only supports int4-tile-packed on CUDA
           - model:
               repo: "mistralai"
               name: "Voxtral-Mini-4B-Realtime-2602"
@@ -256,12 +251,7 @@ jobs:
       download-artifact: ${{ matrix.model.repo }}-${{ matrix.model.name }}-cuda-${{ matrix.quant }}
       ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
       script: |
-        # Voxtral Realtime uses offline mode for CUDA CI (not streaming)
-        VR_MODE=""
-        if [ "${{ matrix.model.name }}" = "Voxtral-Mini-4B-Realtime-2602" ]; then
-          VR_MODE="vr-offline"
-        fi
-        source .ci/scripts/test_model_e2e.sh cuda "${{ matrix.model.repo }}/${{ matrix.model.name }}" "${{ matrix.quant }}" "${RUNNER_ARTIFACT_DIR}" "$VR_MODE"
+        source .ci/scripts/test_model_e2e.sh cuda "${{ matrix.model.repo }}/${{ matrix.model.name }}" "${{ matrix.quant }}" "${RUNNER_ARTIFACT_DIR}"
 
   test-cuda-pybind:
     name: test-cuda-pybind