diff --git a/.buildkite/hardware_tests/intel_xpu_ci/test-intel.yaml b/.buildkite/hardware_tests/intel_xpu_ci/test-intel.yaml new file mode 100644 index 0000000000..11c88a6043 --- /dev/null +++ b/.buildkite/hardware_tests/intel_xpu_ci/test-intel.yaml @@ -0,0 +1,68 @@ +group: Intel +steps: + - label: ":docker: Build XPU image" + soft_fail: true + optional: true + depends_on: [] + key: image-build-xpu + commands: + - bash -lc '.buildkite/image_build/image_build_xpu.sh "public.ecr.aws/q9t5s3a7" "vllm-ci-test-repo" "$BUILDKITE_COMMIT"' + env: + DOCKER_BUILDKIT: "1" + retry: + automatic: + - exit_status: -1 # Agent was lost + limit: 2 + - exit_status: -10 # Agent was lost + limit: 2 + - label: "XPU example Test" + depends_on: + - image-build-xpu + timeout_in_minutes: 30 + optional: true + device: intel_gpu + no_plugin: true + env: + REGISTRY: "public.ecr.aws/q9t5s3a7" + REPO: "vllm-ci-test-repo" + source_file_dependencies: + - .buildkite/hardware_tests/intel_xpu_ci/test-intel.yaml + - .buildkite/scripts/hardware_ci/run-intel-ci-test.sh + commands: + - >- + bash .buildkite/scripts/hardware_ci/run-intel-test.sh + 'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh example' + - label: "XPU V1 test" + depends_on: + - image-build-xpu + timeout_in_minutes: 30 + optional: true + device: intel_gpu + no_plugin: true + env: + REGISTRY: "public.ecr.aws/q9t5s3a7" + REPO: "vllm-ci-test-repo" + source_file_dependencies: + - .buildkite/hardware_tests/intel_xpu_ci/test-intel.yaml + - .buildkite/scripts/hardware_ci/run-intel-ci-test.sh + commands: + - >- + bash .buildkite/scripts/hardware_ci/run-intel-test.sh + 'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh v1' + - label: "XPU server test" + depends_on: + - image-build-xpu + timeout_in_minutes: 30 + optional: true + device: intel_gpu + no_plugin: true + env: + REGISTRY: "public.ecr.aws/q9t5s3a7" + REPO: "vllm-ci-test-repo" + source_file_dependencies: + - .buildkite/hardware_tests/intel_xpu_ci/test-intel.yaml + - .buildkite/scripts/hardware_ci/run-intel-ci-test.sh + commands: + - >- + bash .buildkite/scripts/hardware_ci/run-intel-test.sh + 'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh server' diff --git a/.buildkite/scripts/hardware_ci/run-intel-ci-test.sh b/.buildkite/scripts/hardware_ci/run-intel-ci-test.sh new file mode 100644 index 0000000000..491ac53761 --- /dev/null +++ b/.buildkite/scripts/hardware_ci/run-intel-ci-test.sh @@ -0,0 +1,51 @@ +#!/bin/bash + +set -euo pipefail + +test_suite="${1:-}" + +if [[ -z "${test_suite}" ]]; then + echo "Usage: $0 " >&2 + exit 1 +fi + +case "${test_suite}" in + example) + pip install tblib==3.1.0 + + python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager + python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 -O3 -cc.cudagraph_mode=NONE + python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp + python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --attention-backend=TRITON_ATTN + python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --quantization fp8 + python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --kv-cache-dtype fp8 + python3 examples/basic/offline_inference/generate.py --model nvidia/Llama-3.1-8B-Instruct-FP8 --block-size 64 --enforce-eager --quantization modelopt --kv-cache-dtype fp8 --attention-backend TRITON_ATTN --max-model-len 4096 + python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --block-size 64 --enforce-eager --max-model-len 8192 + python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 + python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 --enable-expert-parallel + python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --max-model-len 8192 + ;; + v1) + cd tests + + pytest -v -s v1/core --ignore=v1/core/test_reset_prefix_cache_e2e.py --ignore=v1/core/test_scheduler_e2e.py + pytest -v -s v1/engine --ignore=v1/engine/test_output_processor.py + pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py -k "not test_topk_only and not test_topp_only and not test_topk_and_topp" + pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py --ignore=v1/worker/test_worker_memory_snapshot.py + pytest -v -s v1/structured_output + pytest -v -s v1/test_serial_utils.py + pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_speculators_eagle3.py --ignore=v1/spec_decode/test_acceptance_length.py + pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_multi_connector.py --ignore=v1/kv_connector/unit/test_example_connector.py --ignore=v1/kv_connector/unit/test_lmcache_integration.py --ignore=v1/kv_connector/unit/test_hf3fs_client.py --ignore=v1/kv_connector/unit/test_hf3fs_connector.py --ignore=v1/kv_connector/unit/test_hf3fs_metadata_server.py --ignore=v1/kv_connector/unit/test_offloading_connector.py + ;; + server) + pip install av + cd tests + + pytest -v -s entrypoints/openai/chat_completion/test_audio_in_video.py + pytest -v -s benchmarks/test_serve_cli.py + ;; + *) + echo "Unknown Intel test suite: ${test_suite}" >&2 + exit 1 + ;; +esac