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, 11:00 UTC
Correcting testcases in builkite job for IBM Power (#17675)
Signed-off-by: Aaruni Aggarwal <aaruniagg@gmail.com>
Aaruni Aggarwal committed
May 12, 2025 at 13:41 UTC
9fbf2bfbd509845fc37139e1ec51f60e41af0815
1 file changed
+6
-3
.buildkite/scripts/hardware_ci/run-cpu-test-ppc64le.sh
+6
-3
@@ -32,9 +32,12 @@ function cpu_tests() {
32
set -e
33
pip install pytest pytest-asyncio einops peft Pillow soundfile transformers_stream_generator matplotlib
34
pip install sentence-transformers datamodel_code_generator
35
- pytest -v -s tests/models/embedding/language/test_cls_models.py::test_classification_models[float-jason9693/Qwen2.5-1.5B-apeach]
36
- pytest -v -s tests/models/embedding/language/test_embedding.py::test_models[half-BAAI/bge-base-en-v1.5]
37
- pytest -v -s tests/models/encoder_decoder/language -m cpu_model"
35
+ pytest -v -s tests/models/language/generation/test_bart.py -m cpu_model
36
+ pytest -v -s tests/models/language/generation/test_common.py::test_models[False-5-32-openai-community/gpt2]
37
+ pytest -v -s tests/models/language/generation/test_common.py::test_models[False-5-32-facebook/opt-125m]
38
+ pytest -v -s tests/models/language/generation/test_common.py::test_models[False-5-32-google/gemma-1.1-2b-it]
39
+ pytest -v -s tests/models/language/pooling/test_classification.py::test_models[float-jason9693/Qwen2.5-1.5B-apeach]
40
+ pytest -v -s tests/models/language/pooling/test_embedding.py::test_models[half-BAAI/bge-base-en-v1.5]"
41
}
42
43
# All of CPU tests are expected to be finished less than 40 mins.