[XPU][TEST] Add entrypoints test in Intel GPU CI (#53980)
Signed-off-by: zengxian <xiangdong.zeng@intel.com> Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
@@ -0,0 +1,185 @@
|
||||
group: Entrypoints
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
steps:
|
||||
- label: ":intel: (BMG) Entrypoints Unit"
|
||||
key: entrypoints-unit-tests-intel
|
||||
timeout_in_minutes: 45
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
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/entrypoints
|
||||
- tests/entrypoints/unit_tests
|
||||
- tests/entrypoints/weight_transfer
|
||||
- tests/entrypoints/launchers
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
pytest -v -s entrypoints/unit_tests &&
|
||||
pytest -v -s entrypoints/weight_transfer'
|
||||
|
||||
- label: ":intel: (BMG) Entrypoints Integration (LLM)"
|
||||
key: entrypoints-integration-llm-intel
|
||||
timeout_in_minutes: 70
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
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/
|
||||
- tests/entrypoints/llm
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||
cd tests &&
|
||||
pytest -v -s entrypoints/llm/test_generate.py &&
|
||||
pytest -v -s entrypoints/llm/offline_mode'
|
||||
|
||||
- label: ":intel: (BMG) Entrypoints Integration (API Server)"
|
||||
key: entrypoints-integration-api-server-intel
|
||||
timeout_in_minutes: 70
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
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/
|
||||
- "!vllm/distributed/kv_transfer/"
|
||||
- tests/entrypoints/serve
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||
cd tests &&
|
||||
pytest -v -s entrypoints/serve --ignore=entrypoints/serve/dev/rpc
|
||||
--deselect="tests/entrypoints/serve/dev/rlhf/state_transitions/test_pause_resume.py::TestPauseResume::test_clear_cache_preserves_output_and_controls_prefix_cache[MRV1]" &&
|
||||
PYTHONPATH=/workspace/vllm pytest -v -s entrypoints/serve/dev/rpc'
|
||||
|
||||
- label: ":intel: (BMG) Entrypoints Integration (API Server Scale Out)"
|
||||
key: entrypoints-integration-api-server-scale-out-intel
|
||||
timeout_in_minutes: 40
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
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/
|
||||
- "!vllm/distributed/kv_transfer/"
|
||||
- tests/entrypoints/scale_out
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||
cd tests &&
|
||||
pytest -v -s entrypoints/scale_out'
|
||||
|
||||
- label: ":intel: (BMG) Entrypoints Integration (API Server Generate)"
|
||||
key: entrypoints-integration-api-server-generate-intel
|
||||
timeout_in_minutes: 65
|
||||
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/
|
||||
- "!vllm/distributed/kv_transfer/"
|
||||
- tests/tool_use
|
||||
- tests/entrypoints/tool_parsers
|
||||
- tests/entrypoints/anthropic
|
||||
- tests/entrypoints/generate
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
pytest -v -s tool_use
|
||||
--deselect="tests/tool_use/mistral/test_mistral_tool_calls.py::test_tool_call_none_with_tools[ministral-3b]"
|
||||
--deselect="tests/tool_use/test_chat_completions.py::test_chat_completion_with_tools[granite-3.0-8b]" &&
|
||||
pytest -v -s entrypoints/tool_parsers &&
|
||||
pytest -v -s entrypoints/generate &&
|
||||
pytest -v -s entrypoints/anthropic'
|
||||
|
||||
- label: ":intel: (BMG) Entrypoints Integration (Responses API)"
|
||||
key: entrypoints-integration-responses-api-intel
|
||||
timeout_in_minutes: 60
|
||||
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/
|
||||
- "!vllm/distributed/kv_transfer/"
|
||||
- tests/entrypoints/openai/responses
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
pytest -v -s entrypoints/openai/responses'
|
||||
|
||||
- label: ":intel: (BMG) OpenAI API Correctness"
|
||||
key: openai-api-correctness-intel
|
||||
timeout_in_minutes: 30
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
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:
|
||||
- csrc/
|
||||
- vllm/entrypoints/openai/
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
pytest -v -s entrypoints/openai/correctness/'
|
||||
Reference in New Issue
Block a user