[XPU][CI] Enable shared loader test (#45977)

Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
This commit is contained in:
Chaojun Zhang
2026-06-30 11:20:33 +00:00
committed by GitHub
parent 8cf7c4d8ad
commit ea9ddf59fc
2 changed files with 28 additions and 1 deletions
@@ -0,0 +1,27 @@
group: Models - Distributed
depends_on:
- image-build-xpu
steps:
- label: Distributed Model Tests (2 GPUs)
key: distributed-model-tests-2-gpus
timeout_in_minutes: 50
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/model_executor/model_loader/sharded_state_loader.py
- vllm/model_executor/models/
- tests/model_executor/model_loader/test_sharded_state_loader.py
commands:
- >-
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
'cd tests &&
pytest -v -s model_executor/model_loader/test_sharded_state_loader.py -m "not slow_test"'
@@ -97,7 +97,7 @@ def test_sharded_state_loader(
ctx = mp.get_context("spawn")
platform_args = {}
if current_platform.is_rocm():
if current_platform.is_rocm() or current_platform.is_xpu():
platform_args["max_num_seqs"] = 1
# Run in separate processes for memory & CUDA isolation