[XPU][CI]Remove model_runner_v2 test from Intel GPU CI (#58050)

Signed-off-by: zengxian <xiangdong.zeng@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
xiangdong
2026-09-22 19:56:01 +08:00
committed by GitHub
co-authored by Kunshang Ji
parent 9815732c16
commit 362a64b21d
@@ -1,120 +0,0 @@
group: Model Runner V2 Intel
depends_on:
- image-build-xpu
steps:
- label: Model Runner V2 Core Tests (Intel)
key: model-runner-v2-core-tests-intel
timeout_in_minutes: 45
device: intel_gpu
agent_tags:
label: production
gpu: 2+
mem: 24+
no_plugin: true
working_dir: "."
env:
REGISTRY: "public.ecr.aws/q9t5s3a7"
REPO: "vllm-ci-test-repo"
VLLM_TEST_DEVICE: "xpu"
source_file_dependencies:
- vllm/v1/worker/gpu/
- vllm/v1/worker/gpu_worker.py
- vllm/v1/core/sched/
- vllm/v1/attention/
- tests/v1/engine/test_llm_engine.py
- tests/v1/e2e/
commands:
- >-
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
'export VLLM_USE_V2_MODEL_RUNNER=1 &&
cd tests &&
pytest -v -s v1/engine/test_llm_engine.py -k "not test_engine_metrics" &&
pytest -v -s v1/e2e/general/test_context_length.py &&
ENFORCE_EAGER=1 pytest -v -s v1/e2e/general/test_async_scheduling.py -k "not ngram" &&
pytest -v -s entrypoints/llm/test_struct_output_generate.py -k "xgrammar and not speculative_config6 and not speculative_config7 and not speculative_config8 and not speculative_config0" &&
pytest -v -s v1/e2e/general/test_min_tokens.py'
- label: Model Runner V2 Examples (Intel)
key: model-runner-v2-examples-intel
timeout_in_minutes: 45
device: intel_gpu
agent_tags:
label: production
gpu: 1+
mem: 24+
no_plugin: true
working_dir: "."
env:
REGISTRY: "public.ecr.aws/q9t5s3a7"
REPO: "vllm-ci-test-repo"
VLLM_TEST_DEVICE: "xpu"
source_file_dependencies:
- vllm/v1/worker/gpu/
- vllm/v1/core/sched/
- vllm/v1/worker/gpu_worker.py
- examples/basic/offline_inference/
- examples/generate/multimodal/
- examples/features/
commands:
- >-
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
'export VLLM_USE_V2_MODEL_RUNNER=1 &&
cd examples &&
python3 basic/offline_inference/chat.py &&
python3 basic/offline_inference/generate.py --model facebook/opt-125m &&
python3 generate/multimodal/vision_language_offline.py --seed 0 &&
python3 features/automatic_prefix_caching/prefix_caching_offline.py'
- label: Model Runner V2 Distributed (2 GPUs)
key: model-runner-v2-distributed-2-gpus
timeout_in_minutes: 50
device: intel_gpu
agent_tags:
label: production
gpu: 2+
mem: 16+
no_plugin: true
working_dir: "."
env:
REGISTRY: "public.ecr.aws/q9t5s3a7"
REPO: "vllm-ci-test-repo"
VLLM_TEST_DEVICE: "xpu"
source_file_dependencies:
- vllm/v1/worker/gpu/
- vllm/v1/worker/gpu_worker.py
- tests/basic_correctness/test_basic_correctness.py
- tests/v1/distributed/test_async_llm_dp.py
- tests/v1/distributed/test_eagle_dp.py
commands:
- >-
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
'export VLLM_USE_V2_MODEL_RUNNER=1 &&
cd tests &&
TARGET_TEST_SUITE=L4 pytest -v -s basic_correctness/test_basic_correctness.py -m "distributed\(num_gpus=2\)" -k "not ray and not True"'
- label: Model Runner V2 Spec Decode
key: model-runner-v2-spec-decode
timeout_in_minutes: 50
device: intel_gpu
agent_tags:
label: production
gpu: 1+
mem: 24+
no_plugin: true
working_dir: "."
env:
REGISTRY: "public.ecr.aws/q9t5s3a7"
REPO: "vllm-ci-test-repo"
VLLM_TEST_DEVICE: "xpu"
source_file_dependencies:
- vllm/v1/worker/gpu/
- vllm/v1/worker/gpu_worker.py
- tests/v1/spec_decode/test_max_len.py
- tests/v1/spec_decode/test_rejection_sampler_utils.py
- tests/v1/spec_decode/test_synthetic_rejection_sampler_utils.py
commands:
- >-
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
'export VLLM_USE_V2_MODEL_RUNNER=1 &&
cd tests &&
pytest -v -s v1/spec_decode/test_synthetic_rejection_sampler_utils.py'