diff --git a/.buildkite/intel_jobs/test-intel.yaml b/.buildkite/intel_jobs/test-intel.yaml index 8f4e83eee8..a76331f4d5 100644 --- a/.buildkite/intel_jobs/test-intel.yaml +++ b/.buildkite/intel_jobs/test-intel.yaml @@ -148,16 +148,10 @@ steps: source_file_dependencies: - vllm/ - .buildkite/intel_jobs/test-intel.yaml - # TODO: XPU fused MoE + model runner V2 currently hangs on some - # pre-quantized models, e.g. - # quantization/test_online.py::test_online_quantization_loads_real_weights[nm-testing/tinysmokeqwen3moe-W4A16-first-only-CTstable] - # Remove the VLLM_USE_V2_MODEL_RUNNER=0 override below once the hang is - # root-caused and fixed. commands: - >- bash .buildkite/scripts/hardware_ci/run-intel-test.sh 'cd tests && - export VLLM_USE_V2_MODEL_RUNNER=0 && pytest -v -s quantization/test_auto_round.py && pytest -v -s quantization/test_online.py' - label: "XPU compressed tensors FP8 test"