[XPU][CI] Add more test cases in Intel GPU CI (#43663)
Signed-off-by: zengxian <xiangdong.zeng@intel.com>
This commit is contained in:
@@ -0,0 +1,23 @@
|
|||||||
|
group: Expert Parallelism
|
||||||
|
depends_on:
|
||||||
|
- image-build-xpu
|
||||||
|
steps:
|
||||||
|
- label: EPLB Algorithm
|
||||||
|
key: eplb-algorithm
|
||||||
|
timeout_in_minutes: 45
|
||||||
|
device: intel_gpu
|
||||||
|
no_plugin: true
|
||||||
|
working_dir: "."
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/distributed/eplb
|
||||||
|
- tests/distributed/test_eplb_algo.py
|
||||||
|
- tests/distributed/test_eplb_utils.py
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'cd tests &&
|
||||||
|
pytest -v -s distributed/test_eplb_algo.py'
|
||||||
@@ -38,7 +38,17 @@ steps:
|
|||||||
REPO: "vllm-ci-test-repo"
|
REPO: "vllm-ci-test-repo"
|
||||||
VLLM_TEST_DEVICE: "xpu"
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
source_file_dependencies:
|
source_file_dependencies:
|
||||||
- vllm/
|
- vllm/config/
|
||||||
|
- vllm/distributed/
|
||||||
|
- vllm/engine/
|
||||||
|
- vllm/inputs/
|
||||||
|
- vllm/logger.py
|
||||||
|
- vllm/model_executor/
|
||||||
|
- vllm/platforms/
|
||||||
|
- vllm/sampling_params.py
|
||||||
|
- vllm/transformers_utils/
|
||||||
|
- vllm/utils/
|
||||||
|
- vllm/v1/
|
||||||
- tests/v1/sample
|
- tests/v1/sample
|
||||||
- tests/v1/logits_processors
|
- tests/v1/logits_processors
|
||||||
- tests/v1/test_oracle.py
|
- tests/v1/test_oracle.py
|
||||||
@@ -76,3 +86,101 @@ steps:
|
|||||||
cd tests &&
|
cd tests &&
|
||||||
pytest -v -s v1/kv_offload &&
|
pytest -v -s v1/kv_offload &&
|
||||||
pytest -v -s v1/kv_connector/unit/test_offloading_connector.py'
|
pytest -v -s v1/kv_connector/unit/test_offloading_connector.py'
|
||||||
|
|
||||||
|
- label: Regression
|
||||||
|
key: regression
|
||||||
|
timeout_in_minutes: 30
|
||||||
|
device: intel_gpu
|
||||||
|
no_plugin: true
|
||||||
|
working_dir: "."
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/config/
|
||||||
|
- vllm/distributed/
|
||||||
|
- vllm/engine/
|
||||||
|
- vllm/inputs/
|
||||||
|
- vllm/model_executor/
|
||||||
|
- vllm/multimodal/
|
||||||
|
- vllm/platforms/
|
||||||
|
- vllm/sampling_params.py
|
||||||
|
- vllm/transformers_utils/
|
||||||
|
- vllm/utils/
|
||||||
|
- vllm/v1/
|
||||||
|
- tests/test_regression
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'pip install modelscope &&
|
||||||
|
cd tests &&
|
||||||
|
pytest -v -s test_regression.py'
|
||||||
|
|
||||||
|
- label: Metrics, Tracing (2 GPUs)
|
||||||
|
key: metrics-tracing-2-gpus
|
||||||
|
timeout_in_minutes: 30
|
||||||
|
num_devices: 2
|
||||||
|
device: intel_gpu
|
||||||
|
no_plugin: true
|
||||||
|
working_dir: "."
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/config/
|
||||||
|
- vllm/distributed/
|
||||||
|
- vllm/engine/
|
||||||
|
- vllm/inputs/
|
||||||
|
- vllm/model_executor/
|
||||||
|
- vllm/multimodal/
|
||||||
|
- vllm/platforms/
|
||||||
|
- vllm/sampling_params.py
|
||||||
|
- vllm/tracing/
|
||||||
|
- vllm/transformers_utils/
|
||||||
|
- vllm/utils/
|
||||||
|
- vllm/v1/
|
||||||
|
- tests/v1/tracing
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'pip install opentelemetry-sdk\>=1.26.0 opentelemetry-api\>=1.26.0 opentelemetry-exporter-otlp\>=1.26.0 opentelemetry-semantic-conventions-ai\>=0.4.1 &&
|
||||||
|
cd tests &&
|
||||||
|
pytest -v -s v1/tracing'
|
||||||
|
|
||||||
|
- label: Async Engine, Inputs, Utils, Worker
|
||||||
|
key: async-engine-inputs-utils-worker
|
||||||
|
timeout_in_minutes: 30
|
||||||
|
device: intel_gpu
|
||||||
|
no_plugin: true
|
||||||
|
working_dir: "."
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/assets/
|
||||||
|
- vllm/config/
|
||||||
|
- vllm/distributed/
|
||||||
|
- vllm/engine/
|
||||||
|
- vllm/inputs/
|
||||||
|
- vllm/model_executor/
|
||||||
|
- vllm/multimodal/
|
||||||
|
- vllm/platforms/
|
||||||
|
- vllm/sampling_params.py
|
||||||
|
- vllm/tokenizers/
|
||||||
|
- vllm/transformers_utils/
|
||||||
|
- vllm/utils/
|
||||||
|
- vllm/v1/
|
||||||
|
- tests/detokenizer
|
||||||
|
- tests/multimodal
|
||||||
|
- tests/utils_
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'cd tests &&
|
||||||
|
pip install av &&
|
||||||
|
pytest -v -s detokenizer &&
|
||||||
|
pytest -v -s -m "not cpu_test" ./multimodal &&
|
||||||
|
pytest -v -s utils_ --ignore=utils_/test_mem_utils.py'
|
||||||
|
|||||||
@@ -0,0 +1,111 @@
|
|||||||
|
group: Models - Multimodal
|
||||||
|
depends_on:
|
||||||
|
- image-build-xpu
|
||||||
|
steps:
|
||||||
|
- label: "Multi-Modal Models (Standard) 1: qwen2"
|
||||||
|
key: multi-modal-models-standard-1-qwen2
|
||||||
|
timeout_in_minutes: 45
|
||||||
|
device: intel_gpu
|
||||||
|
no_plugin: true
|
||||||
|
working_dir: "."
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/
|
||||||
|
- tests/models/multimodal
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'pip install av git+https://github.com/TIGER-AI-Lab/Mantis.git &&
|
||||||
|
cd tests &&
|
||||||
|
pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "qwen2" &&
|
||||||
|
pytest -v -s models/multimodal/generation/test_ultravox.py -m core_model'
|
||||||
|
|
||||||
|
- label: "Multi-Modal Models (Standard) 2: qwen3 + gemma"
|
||||||
|
key: multi-modal-models-standard-2-qwen3-gemma
|
||||||
|
timeout_in_minutes: 45
|
||||||
|
device: intel_gpu
|
||||||
|
no_plugin: true
|
||||||
|
working_dir: "."
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/
|
||||||
|
- tests/models/multimodal
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'pip install git+https://github.com/TIGER-AI-Lab/Mantis.git &&
|
||||||
|
cd tests &&
|
||||||
|
pytest -v -s models/multimodal/generation/test_qwen2_5_vl.py -m core_model'
|
||||||
|
|
||||||
|
- label: "Multi-Modal Models (Standard) 3: llava + qwen2_vl"
|
||||||
|
key: multi-modal-models-standard-3-llava-qwen2-vl
|
||||||
|
timeout_in_minutes: 45
|
||||||
|
device: intel_gpu
|
||||||
|
no_plugin: true
|
||||||
|
working_dir: "."
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/
|
||||||
|
- tests/models/multimodal
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'pip install git+https://github.com/TIGER-AI-Lab/Mantis.git &&
|
||||||
|
cd tests &&
|
||||||
|
pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "not qwen2 and not qwen3 and not gemma" &&
|
||||||
|
pytest -v -s models/multimodal/generation/test_qwen2_vl.py -m core_model'
|
||||||
|
|
||||||
|
- label: "Multi-Modal Models (Standard) 4: other + whisper"
|
||||||
|
key: multi-modal-models-standard-4-other-whisper
|
||||||
|
timeout_in_minutes: 45
|
||||||
|
device: intel_gpu
|
||||||
|
no_plugin: true
|
||||||
|
working_dir: "."
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/
|
||||||
|
- tests/models/multimodal
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'pip install av git+https://github.com/TIGER-AI-Lab/Mantis.git &&
|
||||||
|
cd tests &&
|
||||||
|
pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/generation/test_ultravox.py --ignore models/multimodal/generation/test_qwen2_5_vl.py --ignore models/multimodal/generation/test_qwen2_vl.py --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/generation/test_memory_leak.py --ignore models/multimodal/processing'
|
||||||
|
|
||||||
|
- label: Multi-Modal Processor # 44min
|
||||||
|
key: multi-modal-processor
|
||||||
|
timeout_in_minutes: 45
|
||||||
|
device: intel_gpu
|
||||||
|
no_plugin: true
|
||||||
|
working_dir: "."
|
||||||
|
env:
|
||||||
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||||
|
REPO: "vllm-ci-test-repo"
|
||||||
|
VLLM_TEST_DEVICE: "xpu"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/
|
||||||
|
- tests/models/multimodal
|
||||||
|
- tests/models/registry.py
|
||||||
|
commands:
|
||||||
|
- >-
|
||||||
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||||
|
'pip install av matplotlib ftfy git+https://github.com/TIGER-AI-Lab/Mantis.git &&
|
||||||
|
pip install open-clip-torch --no-deps &&
|
||||||
|
cd tests &&
|
||||||
|
pytest -v -s models/multimodal/processing/test_tensor_schema.py
|
||||||
|
--deselect "tests/models/multimodal/processing/test_tensor_schema.py::test_model_tensor_schema[mistralai/Mistral-Large-3-675B-Instruct-2512-NVFP4]"
|
||||||
|
--deselect "tests/models/multimodal/processing/test_tensor_schema.py::test_model_tensor_schema[Qwen/Qwen2.5-Omni-7B-AWQ]"
|
||||||
|
--num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB'
|
||||||
|
parallelism: 4
|
||||||
@@ -372,6 +372,8 @@ export HF_TOKEN ZE_AFFINITY_MASK
|
|||||||
--entrypoint='' \
|
--entrypoint='' \
|
||||||
-e HF_TOKEN \
|
-e HF_TOKEN \
|
||||||
-e ZE_AFFINITY_MASK \
|
-e ZE_AFFINITY_MASK \
|
||||||
|
-e BUILDKITE_PARALLEL_JOB \
|
||||||
|
-e BUILDKITE_PARALLEL_JOB_COUNT \
|
||||||
-e CMDS \
|
-e CMDS \
|
||||||
--name "${container_name}" \
|
--name "${container_name}" \
|
||||||
"${IMAGE}" \
|
"${IMAGE}" \
|
||||||
|
|||||||
Reference in New Issue
Block a user