Pre-download Qwen3-TTS model in CI to avoid intermittent download timeouts (#1727)

Signed-off-by: linyueqian <linyueqian@outlook.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

.buildkite/test-nightly.yml

@@ -68,6 +68,7 @@ steps:
     if: build.env("NIGHTLY") == "1"
     commands:
       - |
+        huggingface-cli download Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice
         export VLLM_WORKER_MULTIPROC_METHOD=spawn
         pytest -s -v tests/e2e/online_serving/test_qwen3_tts.py::TestQwen3TTSNoAsyncChunk
     agents:

.buildkite/test-ready.yml

@@ -214,9 +214,10 @@ 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
+          pytest -s -v tests/e2e/online_serving/test_qwen3_tts.py -k "not NoAsyncChunk"
         '
     agents:
       queue: "gpu_4_queue"