From 36bad1b90cb2958b6de4abdb5a9249b136f39720 Mon Sep 17 00:00:00 2001 From: xiangdong <40376367+zxd1997066@users.noreply.github.com> Date: Fri, 21 Aug 2026 17:31:25 +0800 Subject: [PATCH] [XPU][CI]Add more cases in intel GPU CI and reorganize to align non-xpu part (#51630) Signed-off-by: zengxian Co-authored-by: Kunshang Ji --- .../intel_xpu_ci/test-intel.yaml | 87 +++++++++++++++++++ ...ness.yaml => basic_correctness_intel.yaml} | 4 +- .../intel_jobs/expert_parallelism_intel.yaml | 3 +- .buildkite/intel_jobs/lm_eval_intel.yaml | 28 ++++++ .../intel_jobs/models_multimodal_intel.yaml | 32 ++++++- .buildkite/intel_jobs/test-intel.yaml | 24 ----- .../scripts/hardware_ci/run-intel-ci-test.sh | 27 +++++- 7 files changed, 175 insertions(+), 30 deletions(-) rename .buildkite/intel_jobs/{basic_correctness.yaml => basic_correctness_intel.yaml} (88%) create mode 100644 .buildkite/intel_jobs/lm_eval_intel.yaml diff --git a/.buildkite/hardware_tests/intel_xpu_ci/test-intel.yaml b/.buildkite/hardware_tests/intel_xpu_ci/test-intel.yaml index ed4b4f06d9..e846b47b50 100644 --- a/.buildkite/hardware_tests/intel_xpu_ci/test-intel.yaml +++ b/.buildkite/hardware_tests/intel_xpu_ci/test-intel.yaml @@ -58,6 +58,28 @@ steps: bash .buildkite/scripts/hardware_ci/run-intel-test.sh 'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh v1' parallelism: 2 + - label: "XPU W8A8 FP8 Linear Examples" + depends_on: + - image-build-xpu + timeout_in_minutes: 60 + optional: true + device: intel_gpu + agent_tags: + label: production + gpu: 1+ + mem: 24+ + no_plugin: true + env: + REGISTRY: "public.ecr.aws/q9t5s3a7" + REPO: "vllm-ci-test-repo" + VLLM_TEST_DEVICE: "xpu" + 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 w8a8-fp8-linear' - label: "XPU server test" depends_on: - image-build-xpu @@ -79,3 +101,68 @@ steps: - >- bash .buildkite/scripts/hardware_ci/run-intel-test.sh 'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh server' + - label: "XPU quantization test" + depends_on: + - image-build-xpu + timeout_in_minutes: 60 + optional: true + device: intel_gpu + agent_tags: + label: production + gpu: 1+ + mem: 16+ + 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 quantization' + - label: "XPU compressed tensors FP8 test" + depends_on: + - image-build-xpu + timeout_in_minutes: 60 + optional: true + device: intel_gpu + agent_tags: + label: production + gpu: 1+ + mem: 16+ + no_plugin: true + env: + REGISTRY: "public.ecr.aws/q9t5s3a7" + REPO: "vllm-ci-test-repo" + VLLM_TEST_DEVICE: "xpu" + 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 compressed-tensors-fp8' + - label: "XPU Graph" + depends_on: + - image-build-xpu + timeout_in_minutes: 60 + optional: true + device: intel_gpu + agent_tags: + label: production + gpu: 1+ + mem: 32+ + no_plugin: true + env: + REGISTRY: "public.ecr.aws/q9t5s3a7" + REPO: "vllm-ci-test-repo" + VLLM_TEST_DEVICE: "xpu" + 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 graph' diff --git a/.buildkite/intel_jobs/basic_correctness.yaml b/.buildkite/intel_jobs/basic_correctness_intel.yaml similarity index 88% rename from .buildkite/intel_jobs/basic_correctness.yaml rename to .buildkite/intel_jobs/basic_correctness_intel.yaml index 7d9011d6dc..292920c47e 100644 --- a/.buildkite/intel_jobs/basic_correctness.yaml +++ b/.buildkite/intel_jobs/basic_correctness_intel.yaml @@ -7,7 +7,7 @@ steps: device: intel_gpu agent_tags: label: production - gpu: 1+ + gpu: 2+ mem: 16+ no_plugin: true working_dir: "." @@ -24,4 +24,4 @@ steps: 'cd tests && export VLLM_WORKER_MULTIPROC_METHOD=spawn && pytest -v -s basic_correctness/test_cpu_offload.py && - pytest -v -s basic_correctness/test_mem.py::test_end_to_end' + pytest -v -s basic_correctness/test_mem.py' diff --git a/.buildkite/intel_jobs/expert_parallelism_intel.yaml b/.buildkite/intel_jobs/expert_parallelism_intel.yaml index 24dfb07f5f..0c57b7de12 100644 --- a/.buildkite/intel_jobs/expert_parallelism_intel.yaml +++ b/.buildkite/intel_jobs/expert_parallelism_intel.yaml @@ -24,4 +24,5 @@ steps: - >- bash .buildkite/scripts/hardware_ci/run-intel-test.sh 'cd tests && - pytest -v -s distributed/test_eplb_algo.py' + pytest -v -s distributed/test_eplb_algo.py && + pytest -v -s distributed/test_eplb_utils.py' diff --git a/.buildkite/intel_jobs/lm_eval_intel.yaml b/.buildkite/intel_jobs/lm_eval_intel.yaml new file mode 100644 index 0000000000..966ced8156 --- /dev/null +++ b/.buildkite/intel_jobs/lm_eval_intel.yaml @@ -0,0 +1,28 @@ +group: LM Eval +depends_on: + - image-build-xpu +steps: +- label: "XPU GPQA Eval (GPT-OSS)" + key: xpu-gpqa-eval-gpt-oss + 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: + - csrc/ + - vllm/model_executor/layers/quantization + - tests/evals/gpt_oss/ + commands: + - >- + bash .buildkite/scripts/hardware_ci/run-intel-test.sh + 'pip install "gpt-oss[eval]==0.0.5" && + cd tests && + pytest -s -v evals/gpt_oss/test_gpqa_correctness.py --config-list-file=configs/models-xpu.txt' diff --git a/.buildkite/intel_jobs/models_multimodal_intel.yaml b/.buildkite/intel_jobs/models_multimodal_intel.yaml index 6d04662fa5..d99a7debb0 100644 --- a/.buildkite/intel_jobs/models_multimodal_intel.yaml +++ b/.buildkite/intel_jobs/models_multimodal_intel.yaml @@ -29,12 +29,12 @@ steps: - label: "Multi-Modal Models (Standard) 2: qwen3 + gemma" key: multi-modal-models-standard-2-qwen3-gemma - timeout_in_minutes: 70 + timeout_in_minutes: 90 device: intel_gpu agent_tags: label: production gpu: 1+ - mem: 16+ + mem: 24+ no_plugin: true working_dir: "." env: @@ -48,6 +48,8 @@ steps: - >- bash .buildkite/scripts/hardware_ci/run-intel-test.sh 'cd tests && + pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "qwen3 or gemma" && + pytest -v -s models/multimodal/generation/test_mm_prefix_lm.py -m core_model && pytest -v -s models/multimodal/generation/test_qwen2_5_vl.py -m core_model' - label: "Multi-Modal Models (Standard) 3: llava + qwen2_vl" @@ -125,3 +127,29 @@ steps: pytest -v -s models/multimodal/processing/test_tensor_schema.py --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB' parallelism: 4 + +- label: Multi-Modal Models (Extended Generation 1) + key: multi-modal-models-extended-generation-1 + 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" + optional: true + source_file_dependencies: + - vllm/ + - "!vllm/distributed/kv_transfer/" + - tests/models/multimodal/generation + - tests/models/multimodal/test_mapping.py + commands: + - >- + bash .buildkite/scripts/hardware_ci/run-intel-test.sh + 'cd tests && + pytest -v -s models/multimodal/test_mapping.py' diff --git a/.buildkite/intel_jobs/test-intel.yaml b/.buildkite/intel_jobs/test-intel.yaml index 5815afe5c1..9258d1be88 100644 --- a/.buildkite/intel_jobs/test-intel.yaml +++ b/.buildkite/intel_jobs/test-intel.yaml @@ -151,30 +151,6 @@ steps: 'cd tests && pytest -v -s quantization/test_auto_round.py && pytest -v -s quantization/test_online.py' - - label: "XPU GPQA Eval (GPT-OSS)" - depends_on: - - image-build-xpu - timeout_in_minutes: 60 - device: intel_gpu - agent_tags: - label: production - gpu: 1+ - mem: 24+ - no_plugin: true - env: - REGISTRY: "public.ecr.aws/q9t5s3a7" - REPO: "vllm-ci-test-repo" - VLLM_TEST_DEVICE: "xpu" - source_file_dependencies: - - vllm/ - - tests/evals/gpt_oss/ - - .buildkite/intel_jobs/test-intel.yaml - commands: - - >- - bash .buildkite/scripts/hardware_ci/run-intel-test.sh - 'pip install "gpt-oss[eval]==0.0.5" && - cd tests && - pytest -s -v evals/gpt_oss/test_gpqa_correctness.py --config-list-file=configs/models-xpu.txt' - label: "XPU compressed tensors FP8 test" depends_on: - image-build-xpu diff --git a/.buildkite/scripts/hardware_ci/run-intel-ci-test.sh b/.buildkite/scripts/hardware_ci/run-intel-ci-test.sh index 2f9522b6f1..58c0403b17 100644 --- a/.buildkite/scripts/hardware_ci/run-intel-ci-test.sh +++ b/.buildkite/scripts/hardware_ci/run-intel-ci-test.sh @@ -5,7 +5,7 @@ set -euo pipefail test_suite="${1:-}" if [[ -z "${test_suite}" ]]; then - echo "Usage: $0 " >&2 + echo "Usage: $0 " >&2 exit 1 fi @@ -26,6 +26,13 @@ case "${test_suite}" in 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 ;; + w8a8-fp8-linear) + python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8 --enforce-eager --max-model-len 4096 + python3 examples/basic/offline_inference/generate.py --linear-backend torch --model RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8 --enforce-eager --max-model-len 4096 + python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model neuralmagic/Llama-3.2-1B-Instruct-FP8-dynamic --enforce-eager --max-model-len 4096 + python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model meta-llama/Llama-3.2-1B-Instruct --quantization fp8 --enforce-eager --max-model-len 4096 + python3 examples/basic/offline_inference/generate.py --linear-backend torch --model meta-llama/Llama-3.2-1B-Instruct --quantization fp8 --enforce-eager --max-model-len 4096 + ;; v1) cd tests @@ -46,6 +53,24 @@ case "${test_suite}" in pytest -v -s entrypoints/multimodal/openai/chat_completion/test_audio_in_video.py pytest -v -s benchmarks/test_serve_cli.py ;; + quantization) + cd tests + + pytest -v -s quantization/test_auto_round.py + pytest -v -s quantization/test_online.py + ;; + compressed-tensors-fp8) + cd tests + + pytest -v -s quantization/test_compressed_tensors.py::test_compressed_tensors_fp8 + ;; + graph) + export VLLM_XPU_ENABLE_XPU_GRAPH=1 + + python3 examples/basic/offline_inference/generate.py --model Qwen/Qwen3-0.6B + python3 examples/basic/offline_inference/generate.py --model Qwen/Qwen3-0.6B --kv-cache-dtype fp8 + python3 examples/basic/offline_inference/generate.py --model INCModel/Qwen3-30B-A3B-Instruct-2507-MXFP4-CT-AutoRound --max-model-len 4096 + ;; *) echo "Unknown Intel test suite: ${test_suite}" >&2 exit 1