[Bugfix] Fix colocate-async sleep admission race and deliver AR abort tokens (#6367)

Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Signed-off-by: Cursor <cursoragent@cursor.com>
Signed-off-by: Samit <285365963@qq.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Samit <285365963@qq.com>
This commit is contained in:
authored and GitHub committed 2026-08-29 09:11:39 +00:00
1 parent 5c47fd0bc8
commit bb5bf8fd0a
23 files changed
+1229 -157

No files matched your search

+1 -1
View File
@@ -175,7 +175,7 @@ steps:
grade: Blocking
commands:
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
- pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py tests/e2e/online_serving/test_qwen3_omni.py -m 'advanced_model and cuda' --run-level 'advanced_model'
- pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py tests/e2e/online_serving/test_qwen3_omni.py tests/e2e/offline_inference/test_qwen3_omni_colocate_async.py -m 'advanced_model and cuda' --run-level 'advanced_model'
- label: "Qwen3-TTS CustomVoice E2E Test · Shard %N/%t"
agent_pool: mi300_1
+3 -1
View File
@@ -122,6 +122,7 @@ steps:
- label: "Omni · Qwen3-Omni Test"
source_file_dependencies:
- tests/e2e/offline_inference/test_qwen3_omni.py
- tests/e2e/offline_inference/test_qwen3_omni_colocate_async.py
- tests/e2e/online_serving/test_qwen3_omni.py
- tests/helpers/runtime.py
- vllm_omni/entrypoints/openai/serving_chat.py
@@ -132,9 +133,10 @@ steps:
- vllm_omni/model_executor/models/qwen3_tts/cuda_graph_decoder_wrapper.py
- vllm_omni/model_executor/stage_input_processors/qwen3_omni.py
- vllm_omni/deploy/qwen3_omni_moe.yaml
- vllm_omni/deploy/qwen3_omni_moe_thinking.yaml
timeout_in_minutes: 50
commands:
- pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py tests/e2e/online_serving/test_qwen3_omni.py -m 'advanced_model and cuda' --run-level 'advanced_model'
- pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py tests/e2e/online_serving/test_qwen3_omni.py tests/e2e/offline_inference/test_qwen3_omni_colocate_async.py -m 'advanced_model and cuda' --run-level 'advanced_model'
mirror_hardwares: h100_2
- label: "Omni · MiniCPM-o 4.5 Test"