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 15, 07:15 UTC
[CI][PowerPC] Use a more appropriate way to select testcase in tests/models/language/pooling/test_embedding.py (#19253)
Signed-off-by: Aaruni Aggarwal <aaruniagg@gmail.com>
Aaruni Aggarwal committed
Jun 7, 2025 at 09:22 UTC
c4296b1a273ff2f980a196f350d5df0035086418
1 file changed
+1
-1
.buildkite/scripts/hardware_ci/run-cpu-test-ppc64le.sh
+1
-1
@@ -38,7 +38,7 @@ function cpu_tests() {
38
pytest -v -s tests/models/language/generation/test_common.py::test_models[False-5-32-facebook/opt-125m]
39
pytest -v -s tests/models/language/generation/test_common.py::test_models[False-5-32-google/gemma-1.1-2b-it]
40
pytest -v -s tests/models/language/pooling/test_classification.py::test_models[float-jason9693/Qwen2.5-1.5B-apeach]
41
- pytest -v -s tests/models/language/pooling/test_embedding.py::test_models[half-BAAI/bge-base-en-v1.5]"
41
+ pytest -v -s tests/models/language/pooling/test_embedding.py -m cpu_model"
42
}
43
44
# All of CPU tests are expected to be finished less than 40 mins.