xiangdongandKunshang Ji
69d2b6f82d
Signed-off-by: zengxian <xiangdong.zeng@intel.com> Signed-off-by: xiangdong <40376367+zxd1997066@users.noreply.github.com> Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
52 lines
1.4 KiB
YAML
52 lines
1.4 KiB
YAML
group: LM Eval Intel
|
|
depends_on:
|
|
- image-build-xpu
|
|
steps:
|
|
- label: ":intel: (BMG) 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
|
|
'cd tests &&
|
|
pytest -s -v evals/gpt_oss/test_gpqa_correctness.py --config-list-file=configs/models-xpu.txt'
|
|
- label: ":intel: (BMG) LM Eval Large Models(2 GPUs)"
|
|
key: lm-eval-large-models-2-gpus
|
|
timeout_in_minutes: 45
|
|
device: intel_gpu
|
|
agent_tags:
|
|
label: production
|
|
gpu: 2+
|
|
mem: 24+
|
|
no_plugin: true
|
|
optional: true
|
|
working_dir: "."
|
|
env:
|
|
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
|
REPO: "vllm-ci-test-repo"
|
|
VLLM_TEST_DEVICE: "xpu"
|
|
source_file_dependencies:
|
|
- vllm/
|
|
- .buildkite/lm-eval-harness/
|
|
commands:
|
|
- >-
|
|
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
|
'cd .buildkite/lm-eval-harness &&
|
|
export VLLM_USE_DEEP_GEMM=0 &&
|
|
pytest -s -v test_lm_eval_correctness.py --config-list-file=configs/models-large-xpu-fp8.txt --tp-size=2'
|