From 2a2033df0246d0d2a97278996f59d05585aba63c Mon Sep 17 00:00:00 2001 From: "Chendi.Xue" Date: Mon, 1 Jun 2026 21:16:44 -0500 Subject: [PATCH] [XPU][Rebase v0.22] Fix for 0.22 rebase (#4059) Signed-off-by: Chendi Xue --- .buildkite/pipeline-intel.yaml | 2 +- .../e2e/offline_inference/test_qwen2_5_omni_expansion.py | 3 ++- tests/helpers/mark.py | 8 ++++++-- 3 files changed, 9 insertions(+), 4 deletions(-) diff --git a/.buildkite/pipeline-intel.yaml b/.buildkite/pipeline-intel.yaml index 4f461746d..d94d31bdd 100644 --- a/.buildkite/pipeline-intel.yaml +++ b/.buildkite/pipeline-intel.yaml @@ -10,7 +10,7 @@ steps: DOCKER_BUILDKIT: "1" # Buildkite will automatically replace this with the actual commit hash VLLM_IMAGE_TAG: "${BUILDKITE_COMMIT}" - VLLM_VERSION: "v0.21.0" + VLLM_VERSION: "v0.22.0" priority: 100 timeout_in_minutes: 60 soft_fail: false diff --git a/tests/e2e/offline_inference/test_qwen2_5_omni_expansion.py b/tests/e2e/offline_inference/test_qwen2_5_omni_expansion.py index 0b7e82451..34a878456 100644 --- a/tests/e2e/offline_inference/test_qwen2_5_omni_expansion.py +++ b/tests/e2e/offline_inference/test_qwen2_5_omni_expansion.py @@ -39,7 +39,8 @@ else: stage_config = get_cuda_graph_config() # Create parameter combinations for model and stage config -test_params = [(model, stage_config) for model in models] +# Qwen2.5-Omni with TP=3 needs longer init timeout +test_params = [(model, stage_config, {"stage_init_timeout": 1200, "init_timeout": 1800}) for model in models] def get_question(prompt_type="mix"): diff --git a/tests/helpers/mark.py b/tests/helpers/mark.py index 7d045e6df..3475a0012 100644 --- a/tests/helpers/mark.py +++ b/tests/helpers/mark.py @@ -21,8 +21,10 @@ def cuda_marks(*, res: str, num_cards: int): return marks test_distributed = pytest.mark.distributed_cuda(num_cards=num_cards) + if not current_platform.is_cuda(): + return marks + [test_distributed] test_skipif = pytest.mark.skipif( - not current_platform.is_cuda() or (current_platform.device_count() < num_cards), + current_platform.device_count() < num_cards, reason=f"Need at least {num_cards} CUDA GPUs to run the test.", ) return marks + [test_distributed, test_skipif] @@ -52,8 +54,10 @@ def xpu_marks(*, res: str, num_cards: int): return marks test_distributed = pytest.mark.distributed_xpu(num_cards=num_cards) + if not current_platform.is_xpu(): + return marks + [test_distributed] test_skipif = pytest.mark.skipif( - not current_platform.is_xpu() or (current_platform.device_count() < num_cards), + current_platform.device_count() < num_cards, reason=f"Need at least {num_cards} XPUs to run the test.", ) return marks + [test_distributed, test_skipif]