From 3d1ad0c0f44425ad799b5d606a42d9b8a52c359c Mon Sep 17 00:00:00 2001
From: wangyu <53896905+yenuo26@users.noreply.github.com>
Date: Mon, 31 Aug 2026 20:13:26 +0800
Subject: [PATCH] [CI][Bugfix]Drop dummy-weight Qwen3-TTS Base from Ready CI
 (#6861)

Signed-off-by: wangyu <410167048@qq.com>
---
 .buildkite/cuda/test-merge.yml                |  6 +++++
 .buildkite/cuda/test-ready.yml                | 22 +++----------------
 .../e2e/online_serving/test_qwen3_tts_base.py |  1 -
 3 files changed, 9 insertions(+), 20 deletions(-)

diff --git a/.buildkite/cuda/test-merge.yml b/.buildkite/cuda/test-merge.yml
index 7131041c0..53c70154a 100644
--- a/.buildkite/cuda/test-merge.yml
+++ b/.buildkite/cuda/test-merge.yml
@@ -85,6 +85,9 @@ steps:
           - vllm_omni/model_executor/models/common/alias_free_activation.py
           - vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
           - vllm_omni/deploy/qwen3_tts.yaml
+          - vllm_omni/entrypoints/openai/serving_speech.py
+          - vllm_omni/entrypoints/openai/tts_adapters/
+          - vllm_omni/engine/stage_pool.py
         commands:
           - |
             timeout 40m bash -c "
@@ -104,6 +107,9 @@ steps:
           - vllm_omni/model_executor/models/common/alias_free_activation.py
           - vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
           - vllm_omni/deploy/qwen3_tts.yaml
+          - vllm_omni/entrypoints/openai/serving_speech.py
+          - vllm_omni/entrypoints/openai/tts_adapters/
+          - vllm_omni/engine/stage_pool.py
           - .buildkite/common/scripts/run_cov_split.sh
           - pyproject.toml
         # 40 -> 60: the coverage split runs the model twice.
diff --git a/.buildkite/cuda/test-ready.yml b/.buildkite/cuda/test-ready.yml
index f4b6b0188..7fc46501b 100644
--- a/.buildkite/cuda/test-ready.yml
+++ b/.buildkite/cuda/test-ready.yml
@@ -252,6 +252,9 @@ steps:
           - vllm_omni/model_executor/models/common/alias_free_activation.py
           - vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
           - vllm_omni/deploy/qwen3_tts.yaml
+          - vllm_omni/entrypoints/openai/serving_speech.py
+          - vllm_omni/entrypoints/openai/tts_adapters/
+          - vllm_omni/engine/stage_pool.py
         commands:
           - |
             timeout 20m bash -c "
@@ -260,25 +263,6 @@ steps:
             "
         mirror_hardwares: l4_1
 
-      - label: "TTS · Qwen3-TTS Base Test"
-        source_file_dependencies:
-          - tests/e2e/online_serving/test_qwen3_tts_base.py
-          - vllm_omni/model_executor/models/qwen3_tts/
-          - vllm_omni/model_executor/models/common/qwen3_code_predictor.py
-          - vllm_omni/model_executor/models/common/snake_activation.py
-          - vllm_omni/model_executor/models/common/alias_free_activation.py
-          - vllm_omni/model_executor/stage_input_processors/qwen3_tts.py
-          - vllm_omni/deploy/qwen3_tts.yaml
-        commands:
-          - |
-            timeout 20m bash -c "
-              export VLLM_WORKER_MULTIPROC_METHOD=spawn
-              export VLLM_ALLOW_LONG_MAX_MODEL_LEN=1
-              export VLLM_OMNI_USE_V2_RUNNER=1
-              pytest -s -v tests/e2e/online_serving/test_qwen3_tts_base.py -m 'core_model' --run-level 'core_model'
-            "
-        mirror_hardwares: l4_1
-
       - label: "Diffusion · Wan22 Test"
         source_file_dependencies:
           - tests/e2e/online_serving/test_wan22_t2v.py
diff --git a/tests/e2e/online_serving/test_qwen3_tts_base.py b/tests/e2e/online_serving/test_qwen3_tts_base.py
index 85f3600e0..dd25520f9 100644
--- a/tests/e2e/online_serving/test_qwen3_tts_base.py
+++ b/tests/e2e/online_serving/test_qwen3_tts_base.py
@@ -55,7 +55,6 @@ tts_server_params = [
 
 
 @pytest.mark.advanced_model
-@pytest.mark.core_model
 @pytest.mark.tts
 @hardware_test(res={"cuda": "L4"}, num_cards=1)
 @pytest.mark.parametrize("omni_server", tts_server_params, indirect=True)