[Test] Add Qwen-tts test cases and unify the style of existing test cases

.buildkite/test-merge.yml

@@ -208,6 +208,50 @@ steps:
           volumes:
             - "/fsx/hf_cache:/fsx/hf_cache"
 
+  - label: "Qwen3-TTS CustomVoice E2E Test"
+    depends_on: upload-merge-pipeline
+    commands:
+      - |
+        timeout 20m bash -c '
+          export VLLM_LOGGING_LEVEL=DEBUG
+          export VLLM_WORKER_MULTIPROC_METHOD=spawn
+          pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py -m "advanced_model" --run-level "advanced_model" && pytest -s -v tests/e2e/offline/test_qwen3_tts_customvoice.py
+        '
+    agents:
+      queue: "gpu_1_queue"
+    plugins:
+      - docker#v5.2.0:
+          image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+          always-pull: true
+          propagate-environment: true
+          shm-size: "8gb"
+          environment:
+            - "HF_HOME=/fsx/hf_cache"
+          volumes:
+            - "/fsx/hf_cache:/fsx/hf_cache"
+
+  - label: "Qwen3-TTS Base E2E Test"
+    depends_on: upload-merge-pipeline
+    commands:
+      - |
+        timeout 20m bash -c '
+          export VLLM_LOGGING_LEVEL=DEBUG
+          export VLLM_WORKER_MULTIPROC_METHOD=spawn
+          pytest -s -v tests/e2e/online_serving/test_qwen3_tts_base.py -m "advanced_model" --run-level "advanced_model" && pytest -s -v tests/e2e/offline/test_qwen3_tts_base.py
+        '
+    agents:
+      queue: "gpu_1_queue"
+    plugins:
+      - docker#v5.2.0:
+          image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+          always-pull: true
+          propagate-environment: true
+          shm-size: "8gb"
+          environment:
+            - "HF_HOME=/fsx/hf_cache"
+          volumes:
+            - "/fsx/hf_cache:/fsx/hf_cache"
+
   - label: "Omni Model Test with H100"
     timeout_in_minutes: 30
     depends_on: upload-merge-pipeline

.buildkite/test-nightly.yml

@@ -55,7 +55,8 @@ steps:
     if: build.env("NIGHTLY") == "1"
     commands:
       - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-      - pytest -s -v tests/examples/online_serving/test_qwen2_5_omni.py -m "advanced_model" --run-level "advanced_model"
+      - pytest -s -v examples/ -m "advanced_model and L4" --run-level "advanced_model"
+      - pytest -s -v e2e/online_serving/test_*_expansion.py -m "advanced_model and L4" --run-level "advanced_model"
     agents:
       queue: "gpu_4_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU
     plugins:

.buildkite/test-ready.yml

@@ -260,13 +260,12 @@ steps:
     commands:
       - |
         timeout 20m bash -c '
-          huggingface-cli download Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice
           export VLLM_LOGGING_LEVEL=DEBUG
           export VLLM_WORKER_MULTIPROC_METHOD=spawn
-          pytest -s -v tests/e2e/online_serving/test_qwen3_tts.py -k "not NoAsyncChunk"
+          pytest -s -v tests/e2e/online_serving/test_qwen3_tts_customvoice.py -m "core_model" --run-level "core_model"
         '
     agents:
-      queue: "gpu_4_queue"
+      queue: "gpu_1_queue"
     plugins:
       - docker#v5.2.0:
           image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT

pyproject.toml

@@ -52,6 +52,7 @@ dev = [
     "av", # for ComfyUI tests
     "openpyxl>=3.0.0", # for nightly CI
     "pyttsx3>=2.99",
+    "opencc>=1.2.0",
     "mistune>=3.2.0", # for example tests
 ]