[XPU][CI]Add more cases in intel GPU CI and reorganize to align non-xpu part (#51630)
Signed-off-by: zengxian <xiangdong.zeng@intel.com> Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
@@ -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'
|
||||
|
||||
+2
-2
@@ -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'
|
||||
@@ -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'
|
||||
|
||||
@@ -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'
|
||||
@@ -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'
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -5,7 +5,7 @@ set -euo pipefail
|
||||
test_suite="${1:-}"
|
||||
|
||||
if [[ -z "${test_suite}" ]]; then
|
||||
echo "Usage: $0 <example|v1|server>" >&2
|
||||
echo "Usage: $0 <example|w8a8-fp8-linear|v1|server|quantization|compressed-tensors-fp8|graph>" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
@@ -26,6 +26,13 @@ case "${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
|
||||
|
||||
Reference in New Issue
Block a user