biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI/Build] enable Intel XPU test flow with prebuilt image (#37447)

Browse Source 
Signed-off-by: wendyliu235 <wenjun.liu@intel.com>
This commit is contained in:
wenjun liu
2026-03-27 09:16:04 +08:00
committed by GitHub
parent f73bcb1c51
commit d86060122a
4 changed files with 397 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
.buildkite/intel_jobs/test-intel.yaml Normal file
View File

@@ -0,0 +1,64 @@
group: Intel
steps:
- label: ":docker: Build XPU image"
soft_fail: true
depends_on: []
key: image-build-xpu
commands:
- bash -lc '.buildkite/image_build/image_build_xpu.sh "public.ecr.aws/q9t5s3a7" "vllm-ci-test-repo" "$BUILDKITE_COMMIT"'
env:
DOCKER_BUILDKIT: "1"
retry:
automatic:
- exit_status: -1 # Agent was lost
limit: 2
- exit_status: -10 # Agent was lost
limit: 2
- label: "XPU example Test"
depends_on:
- image-build-xpu
timeout_in_minutes: 30
device: intel_gpu
no_plugin: true
env:
REGISTRY: "public.ecr.aws/q9t5s3a7"
REPO: "vllm-ci-test-repo"
source_file_dependencies:
- vllm/
- .buildkite/intel_jobs/test-intel.yaml
commands:
- >-
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
'pip install tblib==3.1.0 &&
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager &&
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 -O3 -cc.cudagraph_mode=NONE &&
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp &&
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --attention-backend=TRITON_ATTN &&
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --quantization fp8 &&
python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --block-size 64 --enforce-eager --max-model-len 8192 &&
python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 &&
python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 --enable-expert-parallel'
- label: "XPU V1 test"
depends_on:
- image-build-xpu
timeout_in_minutes: 30
device: intel_gpu
no_plugin: true
env:
REGISTRY: "public.ecr.aws/q9t5s3a7"
REPO: "vllm-ci-test-repo"
source_file_dependencies:
- vllm/
- .buildkite/intel_jobs/test-intel.yaml
commands:
- >-
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
'cd tests &&
pytest -v -s v1/core --ignore=v1/core/test_reset_prefix_cache_e2e.py --ignore=v1/core/test_scheduler_e2e.py &&
pytest -v -s v1/engine --ignore=v1/engine/test_output_processor.py &&
pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py &&
pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py --ignore=v1/worker/test_worker_memory_snapshot.py &&
pytest -v -s v1/structured_output &&
pytest -v -s v1/test_serial_utils.py &&
pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_tree_attention.py --ignore=v1/spec_decode/test_speculators_eagle3.py --ignore=v1/spec_decode/test_acceptance_length.py &&
pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_multi_connector.py --ignore=v1/kv_connector/unit/test_nixl_connector.py --ignore=v1/kv_connector/unit/test_example_connector.py --ignore=v1/kv_connector/unit/test_lmcache_integration.py'