A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 3, 05:30 UTC
[XPU][CI] Add 2 server model test files in Intel GPU CI (#42499)
Signed-off-by: zengxian <xiangdong.zeng@intel.com>
xiangdong committed
May 20, 2026 at 16:54 UTC
6f21558da1ec7362d2b4f3d012bce2b612a74459
1 file changed
+19
.buildkite/intel_jobs/test-intel.yaml
+19
@@ -66,3 +66,22 @@ steps:
66
pytest -v -s v1/test_serial_utils.py &&
67
pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_speculators_eagle3.py --ignore=v1/spec_decode/test_acceptance_length.py &&
68
pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_multi_connector.py --ignore=v1/kv_connector/unit/test_example_connector.py --ignore=v1/kv_connector/unit/test_lmcache_integration.py --ignore=v1/kv_connector/unit/test_hf3fs_client.py --ignore=v1/kv_connector/unit/test_hf3fs_connector.py --ignore=v1/kv_connector/unit/test_hf3fs_metadata_server.py --ignore=v1/kv_connector/unit/test_offloading_connector.py'
69
+ - label: "XPU server test"
70
+ depends_on:
71
+ - image-build-xpu
72
+ timeout_in_minutes: 30
73
+ device: intel_gpu
74
+ no_plugin: true
75
+ env:
76
+ REGISTRY: "public.ecr.aws/q9t5s3a7"
77
+ REPO: "vllm-ci-test-repo"
78
+ source_file_dependencies:
79
+ - vllm/
80
+ - .buildkite/intel_jobs/test-intel.yaml
81
+ commands:
82
+ - >-
83
+ bash .buildkite/scripts/hardware_ci/run-intel-test.sh
84
+ 'pip install av &&
85
+ cd tests &&
86
+ pytest -v -s entrypoints/openai/chat_completion/test_audio_in_video.py &&
87
+ pytest -v -s benchmarks/test_serve_cli.py'