[XPU][CI] add model runner v2 into CI (#44650)
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
This commit is contained in:
@@ -0,0 +1,54 @@
|
||||
group: Model Runner V2 Intel
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
steps:
|
||||
- label: Model Runner V2 Core Tests (Intel)
|
||||
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/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" &&
|
||||
ENFORCE_EAGER=1 pytest -v -s v1/e2e/general/test_async_scheduling.py -k "not ngram" &&
|
||||
pytest -v -s v1/e2e/general/test_min_tokens.py'
|
||||
|
||||
- label: Model Runner V2 Examples (Intel)
|
||||
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/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'
|
||||
@@ -243,8 +243,10 @@ container_name="xpu_${BUILDKITE_COMMIT}_$(tr -dc A-Za-z0-9 < /dev/urandom | head
|
||||
|
||||
# ---- Command source selection ----
|
||||
commands=""
|
||||
commands_source=""
|
||||
if [[ -n "${VLLM_TEST_COMMANDS:-}" ]]; then
|
||||
commands="${VLLM_TEST_COMMANDS}"
|
||||
commands_source="env"
|
||||
echo "Commands sourced from VLLM_TEST_COMMANDS (quoting preserved)"
|
||||
elif [[ $# -gt 0 ]]; then
|
||||
all_yaml=true
|
||||
@@ -303,8 +305,12 @@ if [[ -z "$commands" ]]; then
|
||||
fi
|
||||
|
||||
echo "Raw commands: $commands"
|
||||
commands=$(re_quote_pytest_markers "$commands")
|
||||
echo "After re-quoting: $commands"
|
||||
if [[ "$commands_source" != "env" ]]; then
|
||||
commands=$(re_quote_pytest_markers "$commands")
|
||||
echo "After re-quoting: $commands"
|
||||
else
|
||||
echo "Skipping re-quoting for VLLM_TEST_COMMANDS input"
|
||||
fi
|
||||
commands=$(apply_intel_test_overrides "$commands")
|
||||
echo "Final commands: $commands"
|
||||
|
||||
|
||||
Reference in New Issue
Block a user