[CI] Fix test. (#2031)

Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>

.buildkite/test-merge.yml

@@ -374,20 +374,3 @@ steps:
   #               hostPath:
   #                 path: /mnt/hf-cache
   #                 type: DirectoryOrCreate
-
-  - label: "CUDA Unit Test"
-    timeout_in_minutes: 10
-    depends_on: upload-merge-pipeline
-    commands:
-      - pytest -v -s -m 'core_model and cuda'
-    agents:
-      queue: "gpu_1_queue"
-    plugins:
-      - docker#v5.2.0:
-          image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
-          always-pull: true
-          propagate-environment: true
-          environment:
-            - "HF_HOME=/fsx/hf_cache"
-          volumes:
-            - "/fsx/hf_cache:/fsx/hf_cache"

.buildkite/test-ready.yml

@@ -16,6 +16,23 @@ steps:
           volumes:
             - "/fsx/hf_cache:/fsx/hf_cache"
 
+  - label: "Voxtral TTS CUDA Unit Test"
+    timeout_in_minutes: 10
+    depends_on: upload-ready-pipeline
+    commands:
+      - "timeout 10m pytest -s -v tests/model_executor/models/voxtral_tts/test_cuda_graph_acoustic_transformer.py"
+    agents:
+      queue: "gpu_1_queue"
+    plugins:
+      - docker#v5.2.0:
+          image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+          always-pull: true
+          propagate-environment: true
+          environment:
+            - "HF_HOME=/fsx/hf_cache"
+          volumes:
+            - "/fsx/hf_cache:/fsx/hf_cache"
+
   - label: "Diffusion Model Test"
     depends_on: upload-ready-pipeline
     commands:

tests/model_executor/models/voxtral_tts/test_cuda_graph_acoustic_transformer.py

@@ -23,6 +23,7 @@ pytestmark = [
     pytest.mark.skipif(not torch.cuda.is_available(), reason="CUDA required"),
     pytest.mark.core_model,
     pytest.mark.cuda,
+    pytest.mark.L4,
 ]
 
 DEVICE = torch.device("cuda:0")