diff --git a/.buildkite/scripts/hardware_ci/run-xpu-test.sh b/.buildkite/scripts/hardware_ci/run-xpu-test.sh index deb61a9bafab..445cd2735c19 100644 --- a/.buildkite/scripts/hardware_ci/run-xpu-test.sh +++ b/.buildkite/scripts/hardware_ci/run-xpu-test.sh @@ -23,9 +23,13 @@ docker run \ --device /dev/dri \ -v /dev/dri/by-path:/dev/dri/by-path \ --entrypoint="" \ + -e "HF_TOKEN=${HF_TOKEN}" \ + -e "ZE_AFFINITY_MASK=${ZE_AFFINITY_MASK}" \ --name "${container_name}" \ "${image_name}" \ - sh -c ' + bash -c ' + set -e + echo $ZE_AFFINITY_MASK VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend ray VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp @@ -35,8 +39,8 @@ docker run \ pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py pytest -v -s v1/structured_output - pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_eagle.py - pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_multi_connector.py --ignore=v1/kv_connector/unit/test_nixl_connector.py + pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_eagle.py --ignore=v1/spec_decode/test_tree_attention.py + pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_multi_connector.py --ignore=v1/kv_connector/unit/test_nixl_connector.py --ignore=v1/kv_connector/unit/test_shared_storage_connector.py pytest -v -s v1/test_serial_utils.py pytest -v -s v1/test_utils.py pytest -v -s v1/test_metrics_reader.py