diff --git a/.buildkite/intel_jobs/models_distributed_intel.yaml b/.buildkite/intel_jobs/models_distributed_intel.yaml new file mode 100644 index 0000000000..7b574f2a8e --- /dev/null +++ b/.buildkite/intel_jobs/models_distributed_intel.yaml @@ -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"' diff --git a/tests/model_executor/model_loader/test_sharded_state_loader.py b/tests/model_executor/model_loader/test_sharded_state_loader.py index 78134ae383..a0b5a2a4ae 100644 --- a/tests/model_executor/model_loader/test_sharded_state_loader.py +++ b/tests/model_executor/model_loader/test_sharded_state_loader.py @@ -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