@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 5c79b0d648
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 14, 05:30 UTC

[XPU][CI]add xpu env vars in CI scripts (#22946)

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

Kunshang Ji committed Aug 18, 2025 at 17:47 UTC 5c79b0d6484d7d4c5fe007c3c7ad04c72d3bc59e
1 file changed +7 -3
.buildkite/scripts/hardware_ci/run-xpu-test.sh
+7 -3
@@ -23,9 +23,13 @@ docker run \
23 --device /dev/dri \
24 -v /dev/dri/by-path:/dev/dri/by-path \
25 --entrypoint="" \
26 + -e "HF_TOKEN=${HF_TOKEN}" \
27 + -e "ZE_AFFINITY_MASK=${ZE_AFFINITY_MASK}" \
28 --name "${container_name}" \
29 "${image_name}" \
28 - sh -c '
30 + bash -c '
31 + set -e
32 + echo $ZE_AFFINITY_MASK
33 VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager
34 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
35 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 \
39 pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py
40 pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py
41 pytest -v -s v1/structured_output
38 - pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_eagle.py
39 - 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
42 + 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
43 + 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
44 pytest -v -s v1/test_serial_utils.py
45 pytest -v -s v1/test_utils.py
46 pytest -v -s v1/test_metrics_reader.py